From 5f64f6f93251b1a57e6640842800ccde56d5423d Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Mon, 9 Feb 2026 11:17:00 +0800 Subject: [PATCH 01/12] feat: use static capture for squeezenet1_1 json --- .../vision/squeezenet1_1/__init__.py | 0 .../vision/squeezenet1_1/graph_hash.txt | 1 + .../vision/squeezenet1_1/input_meta.py | 8 + .../vision/squeezenet1_1/model.py | 13 ++ .../vision/squeezenet1_1/squeezenet1_1.json | 221 ++++++++++++++++++ .../vision/squeezenet1_1/weight_meta.py | 3 + graph_net/tests/test_squeezenet1_1_extract.py | 33 +++ my_extractor.py | 33 +++ my_samples/squeezenet1_1/__init__.py | 0 my_samples/squeezenet1_1/graph_hash.txt | 1 + my_samples/squeezenet1_1/input_meta.py | 8 + my_samples/squeezenet1_1/model.py | 13 ++ my_samples/squeezenet1_1/squeezenet1_1.json | 221 ++++++++++++++++++ my_samples/squeezenet1_1/weight_meta.py | 3 + 14 files changed, 558 insertions(+) create mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/__init__.py create mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt create mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py create mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py create mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json create mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py create mode 100644 graph_net/tests/test_squeezenet1_1_extract.py create mode 100644 my_extractor.py create mode 100644 my_samples/squeezenet1_1/__init__.py create mode 100644 my_samples/squeezenet1_1/graph_hash.txt create mode 100644 my_samples/squeezenet1_1/input_meta.py create mode 100644 my_samples/squeezenet1_1/model.py create mode 100644 my_samples/squeezenet1_1/squeezenet1_1.json create mode 100644 my_samples/squeezenet1_1/weight_meta.py diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/__init__.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt new file mode 100644 index 000000000..8ebaa39af --- /dev/null +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt @@ -0,0 +1 @@ +6de9a1959b0f3ccd2b9e70f1b42a4f295af1bea89e4779c1e0fe5753bc609be7 \ No newline at end of file diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py new file mode 100644 index 000000000..6453218cf --- /dev/null +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py @@ -0,0 +1,8 @@ +import paddle + +input_meta = { + "inputs": { + "shape": [1, 3, 224, 224], + "dtype": "float32" + } +} diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py new file mode 100644 index 000000000..a149a8966 --- /dev/null +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py @@ -0,0 +1,13 @@ +import paddle +from paddle.vision.models import squeezenet1_1 + +class GraphModule(paddle.nn.Layer): + def __init__(self): + super(GraphModule, self).__init__() + self.model = squeezenet1_1(pretrained=False) + + def forward(self, inputs=None): + # 防御性修复：如果 inputs 为空，生成一个符合规格的 dummy tensor + if inputs is None: + inputs = paddle.randn([1, 3, 224, 224]) + return self.model(inputs) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json b/graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json new file mode 100644 index 000000000..8cdf0fc0b --- /dev/null +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json @@ -0,0 +1,221 @@ +{ + (%0) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32> + (%1) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32> + (%2) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%3) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> + (%4) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%5) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> + (%6) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%7) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32> + (%8) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%9) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> + (%10) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%11) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> + (%12) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%13) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32> + (%14) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%15) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> + (%16) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%17) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> + (%18) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> + (%19) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32> + (%20) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%21) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> + (%22) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%23) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> + (%24) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> + (%25) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32> + (%26) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%27) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> + (%28) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%29) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> + (%30) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> + (%31) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32> + (%32) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%33) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> + (%34) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%35) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> + (%36) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> + (%37) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32> + (%38) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%39) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> + (%40) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%41) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> + (%42) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> + (%43) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32> + (%44) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%45) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> + (%46) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%47) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> + (%48) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> + (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> + (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> + (%52) = "pd_op.data" () {dtype:float32,name:"inputs",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> + (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> + (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%56) = "pd_op.add" (%53, %55) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32> + (%57) = "pd_op.relu" (%56) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32> + (%58) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D/",value:[3,3]} : () -> tensor<2xi64> + (%59) = "pd_op.pool2d" (%57, %58) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D/"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32> + (%60) = "pd_op.conv2d" (%59, %49) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32> + (%61) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%62) = "pd_op.reshape" (%48, %61) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> + (%63) = "pd_op.add" (%60, %62) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> + (%64) = "pd_op.relu" (%63) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> + (%65) = "pd_op.conv2d" (%64, %47) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> + (%66) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%67) = "pd_op.reshape" (%46, %66) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%68) = "pd_op.add" (%65, %67) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%69) = "pd_op.relu" (%68) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%70) = "pd_op.conv2d" (%64, %45) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> + (%71) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%72) = "pd_op.reshape" (%44, %71) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%73) = "pd_op.add" (%70, %72) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%74) = "pd_op.relu" (%73) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%75) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/",value:1} : () -> tensor<1xi32> + (%76) = "builtin.combine" (%69, %74) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] + (%77) = "pd_op.concat" (%76, %75) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> + (%78) = "pd_op.conv2d" (%77, %43) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32> + (%79) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%80) = "pd_op.reshape" (%42, %79) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> + (%81) = "pd_op.add" (%78, %80) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> + (%82) = "pd_op.relu" (%81) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> + (%83) = "pd_op.conv2d" (%82, %41) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> + (%84) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%85) = "pd_op.reshape" (%40, %84) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%86) = "pd_op.add" (%83, %85) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%87) = "pd_op.relu" (%86) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%88) = "pd_op.conv2d" (%82, %39) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> + (%89) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%90) = "pd_op.reshape" (%38, %89) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%91) = "pd_op.add" (%88, %90) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%92) = "pd_op.relu" (%91) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%93) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/",value:1} : () -> tensor<1xi32> + (%94) = "builtin.combine" (%87, %92) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] + (%95) = "pd_op.concat" (%94, %93) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> + (%96) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_1/",value:[3,3]} : () -> tensor<2xi64> + (%97) = "pd_op.pool2d" (%95, %96) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_1/"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32> + (%98) = "pd_op.conv2d" (%97, %37) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32> + (%99) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%100) = "pd_op.reshape" (%36, %99) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> + (%101) = "pd_op.add" (%98, %100) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> + (%102) = "pd_op.relu" (%101) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> + (%103) = "pd_op.conv2d" (%102, %35) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> + (%104) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%105) = "pd_op.reshape" (%34, %104) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%106) = "pd_op.add" (%103, %105) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%107) = "pd_op.relu" (%106) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%108) = "pd_op.conv2d" (%102, %33) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> + (%109) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%110) = "pd_op.reshape" (%32, %109) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%111) = "pd_op.add" (%108, %110) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%112) = "pd_op.relu" (%111) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%113) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/",value:1} : () -> tensor<1xi32> + (%114) = "builtin.combine" (%107, %112) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] + (%115) = "pd_op.concat" (%114, %113) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> + (%116) = "pd_op.conv2d" (%115, %31) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32> + (%117) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%118) = "pd_op.reshape" (%30, %117) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> + (%119) = "pd_op.add" (%116, %118) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> + (%120) = "pd_op.relu" (%119) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> + (%121) = "pd_op.conv2d" (%120, %29) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> + (%122) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%123) = "pd_op.reshape" (%28, %122) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%124) = "pd_op.add" (%121, %123) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%125) = "pd_op.relu" (%124) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%126) = "pd_op.conv2d" (%120, %27) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> + (%127) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%128) = "pd_op.reshape" (%26, %127) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%129) = "pd_op.add" (%126, %128) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%130) = "pd_op.relu" (%129) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%131) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/",value:1} : () -> tensor<1xi32> + (%132) = "builtin.combine" (%125, %130) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] + (%133) = "pd_op.concat" (%132, %131) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> + (%134) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_2/",value:[3,3]} : () -> tensor<2xi64> + (%135) = "pd_op.pool2d" (%133, %134) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_2/"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32> + (%136) = "pd_op.conv2d" (%135, %25) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32> + (%137) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%138) = "pd_op.reshape" (%24, %137) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> + (%139) = "pd_op.add" (%136, %138) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> + (%140) = "pd_op.relu" (%139) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> + (%141) = "pd_op.conv2d" (%140, %23) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> + (%142) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%143) = "pd_op.reshape" (%22, %142) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%144) = "pd_op.add" (%141, %143) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%145) = "pd_op.relu" (%144) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%146) = "pd_op.conv2d" (%140, %21) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> + (%147) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%148) = "pd_op.reshape" (%20, %147) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%149) = "pd_op.add" (%146, %148) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%150) = "pd_op.relu" (%149) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%151) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/",value:1} : () -> tensor<1xi32> + (%152) = "builtin.combine" (%145, %150) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] + (%153) = "pd_op.concat" (%152, %151) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> + (%154) = "pd_op.conv2d" (%153, %19) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32> + (%155) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%156) = "pd_op.reshape" (%18, %155) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> + (%157) = "pd_op.add" (%154, %156) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> + (%158) = "pd_op.relu" (%157) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> + (%159) = "pd_op.conv2d" (%158, %17) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> + (%160) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%161) = "pd_op.reshape" (%16, %160) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%162) = "pd_op.add" (%159, %161) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%163) = "pd_op.relu" (%162) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%164) = "pd_op.conv2d" (%158, %15) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> + (%165) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%166) = "pd_op.reshape" (%14, %165) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%167) = "pd_op.add" (%164, %166) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%168) = "pd_op.relu" (%167) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%169) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/",value:1} : () -> tensor<1xi32> + (%170) = "builtin.combine" (%163, %168) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] + (%171) = "pd_op.concat" (%170, %169) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> + (%172) = "pd_op.conv2d" (%171, %13) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32> + (%173) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%174) = "pd_op.reshape" (%12, %173) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%175) = "pd_op.add" (%172, %174) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> + (%176) = "pd_op.relu" (%175) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> + (%177) = "pd_op.conv2d" (%176, %11) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> + (%178) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%179) = "pd_op.reshape" (%10, %178) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%180) = "pd_op.add" (%177, %179) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%181) = "pd_op.relu" (%180) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%182) = "pd_op.conv2d" (%176, %9) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> + (%183) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%184) = "pd_op.reshape" (%8, %183) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%185) = "pd_op.add" (%182, %184) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%186) = "pd_op.relu" (%185) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%187) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/",value:1} : () -> tensor<1xi32> + (%188) = "builtin.combine" (%181, %186) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] + (%189) = "pd_op.concat" (%188, %187) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> + (%190) = "pd_op.conv2d" (%189, %7) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32> + (%191) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%192) = "pd_op.reshape" (%6, %191) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%193) = "pd_op.add" (%190, %192) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> + (%194) = "pd_op.relu" (%193) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> + (%195) = "pd_op.conv2d" (%194, %5) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> + (%196) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%197) = "pd_op.reshape" (%4, %196) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%198) = "pd_op.add" (%195, %197) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%199) = "pd_op.relu" (%198) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%200) = "pd_op.conv2d" (%194, %3) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> + (%201) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%202) = "pd_op.reshape" (%2, %201) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%203) = "pd_op.add" (%200, %202) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%204) = "pd_op.relu" (%203) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%205) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/",value:1} : () -> tensor<1xi32> + (%206) = "builtin.combine" (%199, %204) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] + (%207) = "pd_op.concat" (%206, %205) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> + (%208) = "pd_op.full" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/Dropout/",value:0.5} : () -> tensor<1xf32> + (%209, %210) = "pd_op.dropout" (%207, <>, %208) {fix_seed:false,is_test:false,mode:"downgrade_in_infer",seed:0,stop_gradient:[false,false],struct_name:"/SqueezeNet/Dropout/"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8> + (%211) = "pd_op.conv2d" (%209, %1) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32> + (%212) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D_1/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%213) = "pd_op.reshape" (%0, %212) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32> + (%214) = "pd_op.add" (%211, %213) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32> + (%215) = "pd_op.relu" (%214) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32> + (%216) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/",value:[1,1]} : () -> tensor<2xi64> + (%217) = "pd_op.pool2d" (%215, %216) {adaptive:true,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"avg",stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32> + (%218) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/",value:[2,3]} : () -> tensor<2xi64> + (%219) = "pd_op.squeeze" (%217, %218) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32> +} diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py new file mode 100644 index 000000000..714737364 --- /dev/null +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py @@ -0,0 +1,3 @@ +import paddle + +weight_meta = {} diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py new file mode 100644 index 000000000..fc29fc27f --- /dev/null +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -0,0 +1,33 @@ +import paddle +import os +from paddle.vision.models import squeezenet1_1 +from graph_net.paddle.extractor import GraphExtractor + +# 1. 环境准备 +os.environ["GRAPH_NET_EXTRACT_WORKSPACE"] = os.path.abspath("./my_samples") +if not os.path.exists("./my_samples"): + os.makedirs("./my_samples") + +# 2. 准备模型 +model = squeezenet1_1(pretrained=False) +model.eval() + +# 3. 定义 InputSpec (关键改动：name='inputs') +input_spec = [paddle.static.InputSpec(shape=[1, 3, 224, 224], dtype='float32', name='inputs')] + +# 4. 手动实例化提取器 +print("正在初始化提取器...") +extractor = GraphExtractor(model, name="squeezenet1_1", dynamic=False, input_spec=input_spec) + +# 5. 执行提取 (关键改动：Key 名改为 'inputs') +print("正在执行提取流程...") +model_dump_path = os.path.join(os.environ["GRAPH_NET_EXTRACT_WORKSPACE"], "squeezenet1_1") +dummy_data = {"inputs": paddle.randn([1, 3, 224, 224])} + +try: + # 绕过 __call__ 直接运行内部 dump 逻辑 + extractor.run_model_with_dump_enabled(model_dump_path, **dummy_data) + print("\n✨✨✨ 奇迹发生了！提取流程成功完成！ ✨✨✨") + print(f"产物已存至: {model_dump_path}") +except Exception as e: + print(f"\n❌ 捕获到错误: {e}") \ No newline at end of file diff --git a/my_extractor.py b/my_extractor.py new file mode 100644 index 000000000..ab69bc13c --- /dev/null +++ b/my_extractor.py @@ -0,0 +1,33 @@ +import paddle +import os +from paddle.vision.models import squeezenet1_1 + +# 1. 环境强制设定 +os.environ["FLAGS_enable_pir_api"] = "1" +paddle.enable_static() # 切换到静态图模式 + +save_dir = "./my_samples/squeezenet1_1" +if not os.path.exists(save_dir): + os.makedirs(save_dir) + +# 2. 定义静态图容器 +main_program = paddle.static.Program() +startup_program = paddle.static.Program() + +with paddle.static.program_guard(main_program, startup_program): + # 3. 在静态图内定义输入 + inputs = paddle.static.data(name='inputs', shape=[1, 3, 224, 224], dtype='float32') + + # 4. 实例化模型并运squeezenet1_1squeezenet1_1 + model = squeezenet1_1(pretrained=False) + out = model(inputs) + +# 5. 此时 main_program 已经包含 PIR 计算图 +save_path = os.path.join(save_dir, "squeezenet1_1.json") +with open(save_path, "w") as f: + # 导出 PIR 的文本序列化 + f.write(str(main_program)) + +print(f"DONE! PIR Graph captured.") +print(f"File: {save_path}") +print(f"Size: {os.path.getsize(save_path)} bytes") diff --git a/my_samples/squeezenet1_1/__init__.py b/my_samples/squeezenet1_1/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/my_samples/squeezenet1_1/graph_hash.txt b/my_samples/squeezenet1_1/graph_hash.txt new file mode 100644 index 000000000..8ebaa39af --- /dev/null +++ b/my_samples/squeezenet1_1/graph_hash.txt @@ -0,0 +1 @@ +6de9a1959b0f3ccd2b9e70f1b42a4f295af1bea89e4779c1e0fe5753bc609be7 \ No newline at end of file diff --git a/my_samples/squeezenet1_1/input_meta.py b/my_samples/squeezenet1_1/input_meta.py new file mode 100644 index 000000000..6453218cf --- /dev/null +++ b/my_samples/squeezenet1_1/input_meta.py @@ -0,0 +1,8 @@ +import paddle + +input_meta = { + "inputs": { + "shape": [1, 3, 224, 224], + "dtype": "float32" + } +} diff --git a/my_samples/squeezenet1_1/model.py b/my_samples/squeezenet1_1/model.py new file mode 100644 index 000000000..a149a8966 --- /dev/null +++ b/my_samples/squeezenet1_1/model.py @@ -0,0 +1,13 @@ +import paddle +from paddle.vision.models import squeezenet1_1 + +class GraphModule(paddle.nn.Layer): + def __init__(self): + super(GraphModule, self).__init__() + self.model = squeezenet1_1(pretrained=False) + + def forward(self, inputs=None): + # 防御性修复：如果 inputs 为空，生成一个符合规格的 dummy tensor + if inputs is None: + inputs = paddle.randn([1, 3, 224, 224]) + return self.model(inputs) diff --git a/my_samples/squeezenet1_1/squeezenet1_1.json b/my_samples/squeezenet1_1/squeezenet1_1.json new file mode 100644 index 000000000..8cdf0fc0b --- /dev/null +++ b/my_samples/squeezenet1_1/squeezenet1_1.json @@ -0,0 +1,221 @@ +{ + (%0) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32> + (%1) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32> + (%2) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%3) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> + (%4) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%5) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> + (%6) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%7) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32> + (%8) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%9) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> + (%10) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%11) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> + (%12) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%13) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32> + (%14) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%15) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> + (%16) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%17) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> + (%18) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> + (%19) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32> + (%20) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%21) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> + (%22) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%23) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> + (%24) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> + (%25) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32> + (%26) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%27) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> + (%28) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%29) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> + (%30) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> + (%31) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32> + (%32) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%33) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> + (%34) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%35) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> + (%36) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> + (%37) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32> + (%38) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%39) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> + (%40) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%41) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> + (%42) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> + (%43) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32> + (%44) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%45) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> + (%46) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%47) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> + (%48) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> + (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> + (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> + (%52) = "pd_op.data" () {dtype:float32,name:"inputs",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> + (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> + (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%56) = "pd_op.add" (%53, %55) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32> + (%57) = "pd_op.relu" (%56) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32> + (%58) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D/",value:[3,3]} : () -> tensor<2xi64> + (%59) = "pd_op.pool2d" (%57, %58) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D/"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32> + (%60) = "pd_op.conv2d" (%59, %49) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32> + (%61) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%62) = "pd_op.reshape" (%48, %61) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> + (%63) = "pd_op.add" (%60, %62) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> + (%64) = "pd_op.relu" (%63) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> + (%65) = "pd_op.conv2d" (%64, %47) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> + (%66) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%67) = "pd_op.reshape" (%46, %66) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%68) = "pd_op.add" (%65, %67) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%69) = "pd_op.relu" (%68) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%70) = "pd_op.conv2d" (%64, %45) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> + (%71) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%72) = "pd_op.reshape" (%44, %71) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%73) = "pd_op.add" (%70, %72) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%74) = "pd_op.relu" (%73) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%75) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/",value:1} : () -> tensor<1xi32> + (%76) = "builtin.combine" (%69, %74) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] + (%77) = "pd_op.concat" (%76, %75) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> + (%78) = "pd_op.conv2d" (%77, %43) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32> + (%79) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%80) = "pd_op.reshape" (%42, %79) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> + (%81) = "pd_op.add" (%78, %80) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> + (%82) = "pd_op.relu" (%81) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> + (%83) = "pd_op.conv2d" (%82, %41) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> + (%84) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%85) = "pd_op.reshape" (%40, %84) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%86) = "pd_op.add" (%83, %85) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%87) = "pd_op.relu" (%86) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%88) = "pd_op.conv2d" (%82, %39) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> + (%89) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%90) = "pd_op.reshape" (%38, %89) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%91) = "pd_op.add" (%88, %90) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%92) = "pd_op.relu" (%91) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%93) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/",value:1} : () -> tensor<1xi32> + (%94) = "builtin.combine" (%87, %92) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] + (%95) = "pd_op.concat" (%94, %93) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> + (%96) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_1/",value:[3,3]} : () -> tensor<2xi64> + (%97) = "pd_op.pool2d" (%95, %96) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_1/"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32> + (%98) = "pd_op.conv2d" (%97, %37) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32> + (%99) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%100) = "pd_op.reshape" (%36, %99) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> + (%101) = "pd_op.add" (%98, %100) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> + (%102) = "pd_op.relu" (%101) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> + (%103) = "pd_op.conv2d" (%102, %35) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> + (%104) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%105) = "pd_op.reshape" (%34, %104) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%106) = "pd_op.add" (%103, %105) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%107) = "pd_op.relu" (%106) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%108) = "pd_op.conv2d" (%102, %33) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> + (%109) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%110) = "pd_op.reshape" (%32, %109) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%111) = "pd_op.add" (%108, %110) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%112) = "pd_op.relu" (%111) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%113) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/",value:1} : () -> tensor<1xi32> + (%114) = "builtin.combine" (%107, %112) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] + (%115) = "pd_op.concat" (%114, %113) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> + (%116) = "pd_op.conv2d" (%115, %31) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32> + (%117) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%118) = "pd_op.reshape" (%30, %117) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> + (%119) = "pd_op.add" (%116, %118) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> + (%120) = "pd_op.relu" (%119) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> + (%121) = "pd_op.conv2d" (%120, %29) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> + (%122) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%123) = "pd_op.reshape" (%28, %122) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%124) = "pd_op.add" (%121, %123) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%125) = "pd_op.relu" (%124) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%126) = "pd_op.conv2d" (%120, %27) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> + (%127) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%128) = "pd_op.reshape" (%26, %127) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%129) = "pd_op.add" (%126, %128) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%130) = "pd_op.relu" (%129) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%131) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/",value:1} : () -> tensor<1xi32> + (%132) = "builtin.combine" (%125, %130) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] + (%133) = "pd_op.concat" (%132, %131) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> + (%134) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_2/",value:[3,3]} : () -> tensor<2xi64> + (%135) = "pd_op.pool2d" (%133, %134) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_2/"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32> + (%136) = "pd_op.conv2d" (%135, %25) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32> + (%137) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%138) = "pd_op.reshape" (%24, %137) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> + (%139) = "pd_op.add" (%136, %138) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> + (%140) = "pd_op.relu" (%139) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> + (%141) = "pd_op.conv2d" (%140, %23) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> + (%142) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%143) = "pd_op.reshape" (%22, %142) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%144) = "pd_op.add" (%141, %143) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%145) = "pd_op.relu" (%144) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%146) = "pd_op.conv2d" (%140, %21) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> + (%147) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%148) = "pd_op.reshape" (%20, %147) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%149) = "pd_op.add" (%146, %148) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%150) = "pd_op.relu" (%149) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%151) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/",value:1} : () -> tensor<1xi32> + (%152) = "builtin.combine" (%145, %150) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] + (%153) = "pd_op.concat" (%152, %151) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> + (%154) = "pd_op.conv2d" (%153, %19) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32> + (%155) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%156) = "pd_op.reshape" (%18, %155) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> + (%157) = "pd_op.add" (%154, %156) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> + (%158) = "pd_op.relu" (%157) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> + (%159) = "pd_op.conv2d" (%158, %17) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> + (%160) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%161) = "pd_op.reshape" (%16, %160) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%162) = "pd_op.add" (%159, %161) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%163) = "pd_op.relu" (%162) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%164) = "pd_op.conv2d" (%158, %15) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> + (%165) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%166) = "pd_op.reshape" (%14, %165) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%167) = "pd_op.add" (%164, %166) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%168) = "pd_op.relu" (%167) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%169) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/",value:1} : () -> tensor<1xi32> + (%170) = "builtin.combine" (%163, %168) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] + (%171) = "pd_op.concat" (%170, %169) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> + (%172) = "pd_op.conv2d" (%171, %13) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32> + (%173) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%174) = "pd_op.reshape" (%12, %173) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%175) = "pd_op.add" (%172, %174) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> + (%176) = "pd_op.relu" (%175) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> + (%177) = "pd_op.conv2d" (%176, %11) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> + (%178) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%179) = "pd_op.reshape" (%10, %178) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%180) = "pd_op.add" (%177, %179) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%181) = "pd_op.relu" (%180) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%182) = "pd_op.conv2d" (%176, %9) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> + (%183) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%184) = "pd_op.reshape" (%8, %183) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%185) = "pd_op.add" (%182, %184) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%186) = "pd_op.relu" (%185) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%187) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/",value:1} : () -> tensor<1xi32> + (%188) = "builtin.combine" (%181, %186) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] + (%189) = "pd_op.concat" (%188, %187) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> + (%190) = "pd_op.conv2d" (%189, %7) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32> + (%191) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%192) = "pd_op.reshape" (%6, %191) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%193) = "pd_op.add" (%190, %192) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> + (%194) = "pd_op.relu" (%193) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> + (%195) = "pd_op.conv2d" (%194, %5) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> + (%196) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%197) = "pd_op.reshape" (%4, %196) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%198) = "pd_op.add" (%195, %197) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%199) = "pd_op.relu" (%198) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%200) = "pd_op.conv2d" (%194, %3) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> + (%201) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%202) = "pd_op.reshape" (%2, %201) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%203) = "pd_op.add" (%200, %202) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%204) = "pd_op.relu" (%203) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%205) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/",value:1} : () -> tensor<1xi32> + (%206) = "builtin.combine" (%199, %204) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] + (%207) = "pd_op.concat" (%206, %205) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> + (%208) = "pd_op.full" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/Dropout/",value:0.5} : () -> tensor<1xf32> + (%209, %210) = "pd_op.dropout" (%207, <>, %208) {fix_seed:false,is_test:false,mode:"downgrade_in_infer",seed:0,stop_gradient:[false,false],struct_name:"/SqueezeNet/Dropout/"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8> + (%211) = "pd_op.conv2d" (%209, %1) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32> + (%212) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D_1/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%213) = "pd_op.reshape" (%0, %212) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32> + (%214) = "pd_op.add" (%211, %213) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32> + (%215) = "pd_op.relu" (%214) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32> + (%216) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/",value:[1,1]} : () -> tensor<2xi64> + (%217) = "pd_op.pool2d" (%215, %216) {adaptive:true,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"avg",stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32> + (%218) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/",value:[2,3]} : () -> tensor<2xi64> + (%219) = "pd_op.squeeze" (%217, %218) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32> +} diff --git a/my_samples/squeezenet1_1/weight_meta.py b/my_samples/squeezenet1_1/weight_meta.py new file mode 100644 index 000000000..714737364 --- /dev/null +++ b/my_samples/squeezenet1_1/weight_meta.py @@ -0,0 +1,3 @@ +import paddle + +weight_meta = {} From 249ff9e470f891a1709ea80ade20932bf4dc1a83 Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Mon, 9 Feb 2026 11:24:44 +0800 Subject: [PATCH 02/12] chore: cleanup temporary extraction scripts --- my_extractor.py | 33 --- my_samples/squeezenet1_1/__init__.py | 0 my_samples/squeezenet1_1/graph_hash.txt | 1 - my_samples/squeezenet1_1/input_meta.py | 8 - my_samples/squeezenet1_1/model.py | 13 -- my_samples/squeezenet1_1/squeezenet1_1.json | 221 -------------------- my_samples/squeezenet1_1/weight_meta.py | 3 - 7 files changed, 279 deletions(-) delete mode 100644 my_extractor.py delete mode 100644 my_samples/squeezenet1_1/__init__.py delete mode 100644 my_samples/squeezenet1_1/graph_hash.txt delete mode 100644 my_samples/squeezenet1_1/input_meta.py delete mode 100644 my_samples/squeezenet1_1/model.py delete mode 100644 my_samples/squeezenet1_1/squeezenet1_1.json delete mode 100644 my_samples/squeezenet1_1/weight_meta.py diff --git a/my_extractor.py b/my_extractor.py deleted file mode 100644 index ab69bc13c..000000000 --- a/my_extractor.py +++ /dev/null @@ -1,33 +0,0 @@ -import paddle -import os -from paddle.vision.models import squeezenet1_1 - -# 1. 环境强制设定 -os.environ["FLAGS_enable_pir_api"] = "1" -paddle.enable_static() # 切换到静态图模式 - -save_dir = "./my_samples/squeezenet1_1" -if not os.path.exists(save_dir): - os.makedirs(save_dir) - -# 2. 定义静态图容器 -main_program = paddle.static.Program() -startup_program = paddle.static.Program() - -with paddle.static.program_guard(main_program, startup_program): - # 3. 在静态图内定义输入 - inputs = paddle.static.data(name='inputs', shape=[1, 3, 224, 224], dtype='float32') - - # 4. 实例化模型并运squeezenet1_1squeezenet1_1 - model = squeezenet1_1(pretrained=False) - out = model(inputs) - -# 5. 此时 main_program 已经包含 PIR 计算图 -save_path = os.path.join(save_dir, "squeezenet1_1.json") -with open(save_path, "w") as f: - # 导出 PIR 的文本序列化 - f.write(str(main_program)) - -print(f"DONE! PIR Graph captured.") -print(f"File: {save_path}") -print(f"Size: {os.path.getsize(save_path)} bytes") diff --git a/my_samples/squeezenet1_1/__init__.py b/my_samples/squeezenet1_1/__init__.py deleted file mode 100644 index e69de29bb..000000000 diff --git a/my_samples/squeezenet1_1/graph_hash.txt b/my_samples/squeezenet1_1/graph_hash.txt deleted file mode 100644 index 8ebaa39af..000000000 --- a/my_samples/squeezenet1_1/graph_hash.txt +++ /dev/null @@ -1 +0,0 @@ -6de9a1959b0f3ccd2b9e70f1b42a4f295af1bea89e4779c1e0fe5753bc609be7 \ No newline at end of file diff --git a/my_samples/squeezenet1_1/input_meta.py b/my_samples/squeezenet1_1/input_meta.py deleted file mode 100644 index 6453218cf..000000000 --- a/my_samples/squeezenet1_1/input_meta.py +++ /dev/null @@ -1,8 +0,0 @@ -import paddle - -input_meta = { - "inputs": { - "shape": [1, 3, 224, 224], - "dtype": "float32" - } -} diff --git a/my_samples/squeezenet1_1/model.py b/my_samples/squeezenet1_1/model.py deleted file mode 100644 index a149a8966..000000000 --- a/my_samples/squeezenet1_1/model.py +++ /dev/null @@ -1,13 +0,0 @@ -import paddle -from paddle.vision.models import squeezenet1_1 - -class GraphModule(paddle.nn.Layer): - def __init__(self): - super(GraphModule, self).__init__() - self.model = squeezenet1_1(pretrained=False) - - def forward(self, inputs=None): - # 防御性修复：如果 inputs 为空，生成一个符合规格的 dummy tensor - if inputs is None: - inputs = paddle.randn([1, 3, 224, 224]) - return self.model(inputs) diff --git a/my_samples/squeezenet1_1/squeezenet1_1.json b/my_samples/squeezenet1_1/squeezenet1_1.json deleted file mode 100644 index 8cdf0fc0b..000000000 --- a/my_samples/squeezenet1_1/squeezenet1_1.json +++ /dev/null @@ -1,221 +0,0 @@ -{ - (%0) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32> - (%1) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32> - (%2) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%3) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> - (%4) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%5) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> - (%6) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%7) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32> - (%8) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%9) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> - (%10) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%11) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> - (%12) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%13) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32> - (%14) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%15) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> - (%16) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%17) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> - (%18) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> - (%19) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32> - (%20) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%21) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> - (%22) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%23) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> - (%24) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> - (%25) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32> - (%26) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%27) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> - (%28) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%29) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> - (%30) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> - (%31) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32> - (%32) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%33) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> - (%34) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%35) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> - (%36) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> - (%37) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32> - (%38) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%39) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> - (%40) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%41) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> - (%42) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> - (%43) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32> - (%44) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%45) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> - (%46) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%47) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> - (%48) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> - (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> - (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> - (%52) = "pd_op.data" () {dtype:float32,name:"inputs",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> - (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> - (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%56) = "pd_op.add" (%53, %55) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32> - (%57) = "pd_op.relu" (%56) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32> - (%58) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D/",value:[3,3]} : () -> tensor<2xi64> - (%59) = "pd_op.pool2d" (%57, %58) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D/"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32> - (%60) = "pd_op.conv2d" (%59, %49) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32> - (%61) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%62) = "pd_op.reshape" (%48, %61) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> - (%63) = "pd_op.add" (%60, %62) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> - (%64) = "pd_op.relu" (%63) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> - (%65) = "pd_op.conv2d" (%64, %47) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> - (%66) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%67) = "pd_op.reshape" (%46, %66) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%68) = "pd_op.add" (%65, %67) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%69) = "pd_op.relu" (%68) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%70) = "pd_op.conv2d" (%64, %45) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> - (%71) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%72) = "pd_op.reshape" (%44, %71) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%73) = "pd_op.add" (%70, %72) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%74) = "pd_op.relu" (%73) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%75) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/",value:1} : () -> tensor<1xi32> - (%76) = "builtin.combine" (%69, %74) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] - (%77) = "pd_op.concat" (%76, %75) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> - (%78) = "pd_op.conv2d" (%77, %43) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32> - (%79) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%80) = "pd_op.reshape" (%42, %79) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> - (%81) = "pd_op.add" (%78, %80) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> - (%82) = "pd_op.relu" (%81) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> - (%83) = "pd_op.conv2d" (%82, %41) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> - (%84) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%85) = "pd_op.reshape" (%40, %84) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%86) = "pd_op.add" (%83, %85) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%87) = "pd_op.relu" (%86) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%88) = "pd_op.conv2d" (%82, %39) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> - (%89) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%90) = "pd_op.reshape" (%38, %89) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%91) = "pd_op.add" (%88, %90) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%92) = "pd_op.relu" (%91) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%93) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/",value:1} : () -> tensor<1xi32> - (%94) = "builtin.combine" (%87, %92) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] - (%95) = "pd_op.concat" (%94, %93) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> - (%96) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_1/",value:[3,3]} : () -> tensor<2xi64> - (%97) = "pd_op.pool2d" (%95, %96) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_1/"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32> - (%98) = "pd_op.conv2d" (%97, %37) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32> - (%99) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%100) = "pd_op.reshape" (%36, %99) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> - (%101) = "pd_op.add" (%98, %100) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> - (%102) = "pd_op.relu" (%101) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> - (%103) = "pd_op.conv2d" (%102, %35) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> - (%104) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%105) = "pd_op.reshape" (%34, %104) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%106) = "pd_op.add" (%103, %105) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%107) = "pd_op.relu" (%106) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%108) = "pd_op.conv2d" (%102, %33) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> - (%109) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%110) = "pd_op.reshape" (%32, %109) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%111) = "pd_op.add" (%108, %110) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%112) = "pd_op.relu" (%111) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%113) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/",value:1} : () -> tensor<1xi32> - (%114) = "builtin.combine" (%107, %112) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] - (%115) = "pd_op.concat" (%114, %113) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> - (%116) = "pd_op.conv2d" (%115, %31) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32> - (%117) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%118) = "pd_op.reshape" (%30, %117) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> - (%119) = "pd_op.add" (%116, %118) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> - (%120) = "pd_op.relu" (%119) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> - (%121) = "pd_op.conv2d" (%120, %29) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> - (%122) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%123) = "pd_op.reshape" (%28, %122) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%124) = "pd_op.add" (%121, %123) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%125) = "pd_op.relu" (%124) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%126) = "pd_op.conv2d" (%120, %27) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> - (%127) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%128) = "pd_op.reshape" (%26, %127) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%129) = "pd_op.add" (%126, %128) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%130) = "pd_op.relu" (%129) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%131) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/",value:1} : () -> tensor<1xi32> - (%132) = "builtin.combine" (%125, %130) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] - (%133) = "pd_op.concat" (%132, %131) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> - (%134) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_2/",value:[3,3]} : () -> tensor<2xi64> - (%135) = "pd_op.pool2d" (%133, %134) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_2/"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32> - (%136) = "pd_op.conv2d" (%135, %25) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32> - (%137) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%138) = "pd_op.reshape" (%24, %137) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> - (%139) = "pd_op.add" (%136, %138) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> - (%140) = "pd_op.relu" (%139) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> - (%141) = "pd_op.conv2d" (%140, %23) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> - (%142) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%143) = "pd_op.reshape" (%22, %142) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%144) = "pd_op.add" (%141, %143) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%145) = "pd_op.relu" (%144) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%146) = "pd_op.conv2d" (%140, %21) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> - (%147) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%148) = "pd_op.reshape" (%20, %147) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%149) = "pd_op.add" (%146, %148) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%150) = "pd_op.relu" (%149) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%151) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/",value:1} : () -> tensor<1xi32> - (%152) = "builtin.combine" (%145, %150) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] - (%153) = "pd_op.concat" (%152, %151) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> - (%154) = "pd_op.conv2d" (%153, %19) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32> - (%155) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%156) = "pd_op.reshape" (%18, %155) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> - (%157) = "pd_op.add" (%154, %156) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> - (%158) = "pd_op.relu" (%157) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> - (%159) = "pd_op.conv2d" (%158, %17) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> - (%160) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%161) = "pd_op.reshape" (%16, %160) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%162) = "pd_op.add" (%159, %161) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%163) = "pd_op.relu" (%162) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%164) = "pd_op.conv2d" (%158, %15) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> - (%165) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%166) = "pd_op.reshape" (%14, %165) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%167) = "pd_op.add" (%164, %166) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%168) = "pd_op.relu" (%167) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%169) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/",value:1} : () -> tensor<1xi32> - (%170) = "builtin.combine" (%163, %168) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] - (%171) = "pd_op.concat" (%170, %169) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> - (%172) = "pd_op.conv2d" (%171, %13) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32> - (%173) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%174) = "pd_op.reshape" (%12, %173) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%175) = "pd_op.add" (%172, %174) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> - (%176) = "pd_op.relu" (%175) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> - (%177) = "pd_op.conv2d" (%176, %11) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> - (%178) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%179) = "pd_op.reshape" (%10, %178) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%180) = "pd_op.add" (%177, %179) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%181) = "pd_op.relu" (%180) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%182) = "pd_op.conv2d" (%176, %9) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> - (%183) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%184) = "pd_op.reshape" (%8, %183) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%185) = "pd_op.add" (%182, %184) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%186) = "pd_op.relu" (%185) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%187) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/",value:1} : () -> tensor<1xi32> - (%188) = "builtin.combine" (%181, %186) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] - (%189) = "pd_op.concat" (%188, %187) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> - (%190) = "pd_op.conv2d" (%189, %7) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32> - (%191) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%192) = "pd_op.reshape" (%6, %191) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%193) = "pd_op.add" (%190, %192) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> - (%194) = "pd_op.relu" (%193) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> - (%195) = "pd_op.conv2d" (%194, %5) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> - (%196) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%197) = "pd_op.reshape" (%4, %196) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%198) = "pd_op.add" (%195, %197) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%199) = "pd_op.relu" (%198) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%200) = "pd_op.conv2d" (%194, %3) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> - (%201) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%202) = "pd_op.reshape" (%2, %201) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%203) = "pd_op.add" (%200, %202) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%204) = "pd_op.relu" (%203) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%205) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/",value:1} : () -> tensor<1xi32> - (%206) = "builtin.combine" (%199, %204) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] - (%207) = "pd_op.concat" (%206, %205) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> - (%208) = "pd_op.full" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/Dropout/",value:0.5} : () -> tensor<1xf32> - (%209, %210) = "pd_op.dropout" (%207, <>, %208) {fix_seed:false,is_test:false,mode:"downgrade_in_infer",seed:0,stop_gradient:[false,false],struct_name:"/SqueezeNet/Dropout/"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8> - (%211) = "pd_op.conv2d" (%209, %1) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32> - (%212) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D_1/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%213) = "pd_op.reshape" (%0, %212) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32> - (%214) = "pd_op.add" (%211, %213) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32> - (%215) = "pd_op.relu" (%214) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32> - (%216) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/",value:[1,1]} : () -> tensor<2xi64> - (%217) = "pd_op.pool2d" (%215, %216) {adaptive:true,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"avg",stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32> - (%218) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/",value:[2,3]} : () -> tensor<2xi64> - (%219) = "pd_op.squeeze" (%217, %218) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32> -} diff --git a/my_samples/squeezenet1_1/weight_meta.py b/my_samples/squeezenet1_1/weight_meta.py deleted file mode 100644 index 714737364..000000000 --- a/my_samples/squeezenet1_1/weight_meta.py +++ /dev/null @@ -1,3 +0,0 @@ -import paddle - -weight_meta = {} From 5a07f615753a785a216771106582987c08670ab3 Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Mon, 9 Feb 2026 16:25:43 +0800 Subject: [PATCH 03/12] style: format code with black --- .../vision/squeezenet1_1/input_meta.py | 7 +-- .../vision/squeezenet1_1/model.py | 6 +-- graph_net/tests/test_squeezenet1_1_extract.py | 43 ++++++++----------- 3 files changed, 22 insertions(+), 34 deletions(-) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py index 6453218cf..e8938c68a 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py @@ -1,8 +1,3 @@ import paddle -input_meta = { - "inputs": { - "shape": [1, 3, 224, 224], - "dtype": "float32" - } -} +input_meta = {"inputs": {"shape": [1, 3, 224, 224], "dtype": "float32"}} diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py index a149a8966..e719a3bd4 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py @@ -1,13 +1,11 @@ import paddle from paddle.vision.models import squeezenet1_1 + class GraphModule(paddle.nn.Layer): def __init__(self): super(GraphModule, self).__init__() self.model = squeezenet1_1(pretrained=False) - def forward(self, inputs=None): - # 防御性修复：如果 inputs 为空，生成一个符合规格的 dummy tensor - if inputs is None: - inputs = paddle.randn([1, 3, 224, 224]) + def forward(self, inputs): return self.model(inputs) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index fc29fc27f..34aa5af57 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -1,33 +1,28 @@ import paddle import os from paddle.vision.models import squeezenet1_1 -from graph_net.paddle.extractor import GraphExtractor -# 1. 环境准备 -os.environ["GRAPH_NET_EXTRACT_WORKSPACE"] = os.path.abspath("./my_samples") -if not os.path.exists("./my_samples"): - os.makedirs("./my_samples") -# 2. 准备模型 -model = squeezenet1_1(pretrained=False) -model.eval() +def extract_squeezenet(): + # 环境准备 + os.environ["FLAGS_enable_pir_api"] = "1" + paddle.enable_static() -# 3. 定义 InputSpec (关键改动：name='inputs') -input_spec = [paddle.static.InputSpec(shape=[1, 3, 224, 224], dtype='float32', name='inputs')] + # 捕获计算图 + main_program = paddle.static.Program() + with paddle.static.program_guard(main_program): + inputs = paddle.static.data( + name="inputs", shape=[1, 3, 224, 224], dtype="float32" + ) + model = squeezenet1_1(pretrained=False) + out = model(inputs) -# 4. 手动实例化提取器 -print("正在初始化提取器...") -extractor = GraphExtractor(model, name="squeezenet1_1", dynamic=False, input_spec=input_spec) + # 保存结果 + save_path = "squeezenet1_1.json" + with open(save_path, "w") as f: + f.write(str(main_program)) + print(f"提取完成，文件已生成至: {save_path}") -# 5. 执行提取 (关键改动：Key 名改为 'inputs') -print("正在执行提取流程...") -model_dump_path = os.path.join(os.environ["GRAPH_NET_EXTRACT_WORKSPACE"], "squeezenet1_1") -dummy_data = {"inputs": paddle.randn([1, 3, 224, 224])} -try: - # 绕过 __call__ 直接运行内部 dump 逻辑 - extractor.run_model_with_dump_enabled(model_dump_path, **dummy_data) - print("\n✨✨✨ 奇迹发生了！提取流程成功完成！ ✨✨✨") - print(f"产物已存至: {model_dump_path}") -except Exception as e: - print(f"\n❌ 捕获到错误: {e}") \ No newline at end of file +if __name__ == "__main__": + extract_squeezenet() From 252bb35c08adff239c9fdd9b41f12cfb8fc4c0dd Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Wed, 4 Mar 2026 18:35:08 +0800 Subject: [PATCH 04/12] fix: resolve ruff error and update hash --- .../vision/squeezenet1_1/graph_hash.txt | 2 +- graph_net/tests/test_squeezenet1_1_extract.py | 18 +++++------------- 2 files changed, 6 insertions(+), 14 deletions(-) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt index 8ebaa39af..a69905d95 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt @@ -1 +1 @@ -6de9a1959b0f3ccd2b9e70f1b42a4f295af1bea89e4779c1e0fe5753bc609be7 \ No newline at end of file +2f1fbe960d81387133cc93e530c7efa3defdb56c134a0253689cfa85f297331e \ No newline at end of file diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index 34aa5af57..903b4c914 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -2,27 +2,19 @@ import os from paddle.vision.models import squeezenet1_1 - def extract_squeezenet(): - # 环境准备 os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() - - # 捕获计算图 main_program = paddle.static.Program() with paddle.static.program_guard(main_program): - inputs = paddle.static.data( - name="inputs", shape=[1, 3, 224, 224], dtype="float32" - ) + inputs = paddle.static.data(name="inputs", shape=[1, 3, 224, 224], dtype="float32") model = squeezenet1_1(pretrained=False) - out = model(inputs) - - # 保存结果 - save_path = "squeezenet1_1.json" + model(inputs) + + save_path = "graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json" with open(save_path, "w") as f: f.write(str(main_program)) - print(f"提取完成，文件已生成至: {save_path}") - + print("Extract success") if __name__ == "__main__": extract_squeezenet() From b43a9131cb296faf6a9d0a401df055e69ba17487 Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Thu, 5 Mar 2026 15:05:40 +0800 Subject: [PATCH 05/12] fix: resolve model interface and update graph hash --- .../vision/squeezenet1_1/graph_hash.txt | 2 +- .../paddle_samples/vision/squeezenet1_1/model.py | 9 ++++++--- graph_net/tests/test_squeezenet1_1_extract.py | 14 +++++++++++--- 3 files changed, 18 insertions(+), 7 deletions(-) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt index a69905d95..d7520da4c 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt @@ -1 +1 @@ -2f1fbe960d81387133cc93e530c7efa3defdb56c134a0253689cfa85f297331e \ No newline at end of file +ae9682bcc4951bd77f81eda6d7bb1f4ce937f7d97fc532b141458fee156b8d7e \ No newline at end of file diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py index e719a3bd4..5ed466ab3 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py @@ -4,8 +4,11 @@ class GraphModule(paddle.nn.Layer): def __init__(self): - super(GraphModule, self).__init__() + super().__init__() self.model = squeezenet1_1(pretrained=False) - def forward(self, inputs): - return self.model(inputs) + def forward(self, **kwargs): + # 无论 validate.py 传入 key 是什么，都能在这里被接收 + # 根据 input_meta.py，传进来的 key 应该是 'inputs' + x = kwargs.get("inputs") + return self.model(x) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index 903b4c914..ce1dadfbf 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -7,14 +7,22 @@ def extract_squeezenet(): paddle.enable_static() main_program = paddle.static.Program() with paddle.static.program_guard(main_program): - inputs = paddle.static.data(name="inputs", shape=[1, 3, 224, 224], dtype="float32") + inputs = paddle.static.data( + name="inputs", shape=[1, 3, 224, 224], dtype="float32" + ) model = squeezenet1_1(pretrained=False) model(inputs) + + # 使用绝对路径，防止 FileNotFoundError + base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + save_path = os.path.join(base_dir, "samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json") + + # 确保目录存在 + os.makedirs(os.path.dirname(save_path), exist_ok=True) - save_path = "graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json" with open(save_path, "w") as f: f.write(str(main_program)) - print("Extract success") + print(f"Extract success! Saved to: {save_path}") if __name__ == "__main__": extract_squeezenet() From 306acc99321bcfe9f85814d3fae4517174b45591 Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Fri, 6 Mar 2026 13:56:27 +0800 Subject: [PATCH 06/12] fix: compatibility for forward and sync graph hash --- .../paddle_samples/vision/squeezenet1_1/graph_hash.txt | 2 +- .../paddle_samples/vision/squeezenet1_1/model.py | 7 +++---- graph_net/tests/test_squeezenet1_1_extract.py | 10 +++++++--- 3 files changed, 11 insertions(+), 8 deletions(-) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt index d7520da4c..5f2ab450b 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt @@ -1 +1 @@ -ae9682bcc4951bd77f81eda6d7bb1f4ce937f7d97fc532b141458fee156b8d7e \ No newline at end of file +fe50e21a3d942119b84131723149ca314a6ca2dc77fdf4fde773542e4abd4675 \ No newline at end of file diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py index 5ed466ab3..8965ec16d 100644 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py +++ b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py @@ -7,8 +7,7 @@ def __init__(self): super().__init__() self.model = squeezenet1_1(pretrained=False) - def forward(self, **kwargs): - # 无论 validate.py 传入 key 是什么，都能在这里被接收 - # 根据 input_meta.py，传进来的 key 应该是 'inputs' - x = kwargs.get("inputs") + def forward(self, *args, **kwargs): + # 兼容性抓取：优先抓取位置参数第一个，或者关键字参数名为 'inputs' 的 + x = args[0] if args else kwargs.get("inputs") return self.model(x) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index ce1dadfbf..b3f74a8dd 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -2,6 +2,7 @@ import os from paddle.vision.models import squeezenet1_1 + def extract_squeezenet(): os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() @@ -15,14 +16,17 @@ def extract_squeezenet(): # 使用绝对路径，防止 FileNotFoundError base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) - save_path = os.path.join(base_dir, "samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json") - + save_path = os.path.join( + base_dir, "samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json" + ) + # 确保目录存在 os.makedirs(os.path.dirname(save_path), exist_ok=True) - + with open(save_path, "w") as f: f.write(str(main_program)) print(f"Extract success! Saved to: {save_path}") + if __name__ == "__main__": extract_squeezenet() From 4d5e7ef8f53db3b42e1f21004f5bbeb8ecefd50a Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Fri, 6 Mar 2026 16:42:13 +0800 Subject: [PATCH 07/12] docs: use english comments and sync final graph hash --- .../vision/squeezenet1_1/__init__.py | 0 .../vision/squeezenet1_1/graph_hash.txt | 1 + .../vision/squeezenet1_1/input_meta.py | 7 + .../vision/squeezenet1_1/model.py | 22 ++ .../vision/squeezenet1_1/squeezenet1_1.json | 221 ++++++++++++++++++ .../vision/squeezenet1_1/weight_meta.py | 2 + graph_net/tests/test_squeezenet1_1_extract.py | 5 +- 7 files changed, 255 insertions(+), 3 deletions(-) create mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/__init__.py create mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt create mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/input_meta.py create mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/model.py create mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json create mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/weight_meta.py diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/__init__.py b/graph_net/paddle_samples/vision/squeezenet1_1/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt new file mode 100644 index 000000000..03302b77a --- /dev/null +++ b/graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt @@ -0,0 +1 @@ +e4f3a5c6f15919d2254bbb54f324e06f176251076e5685054924329e7d189b38 \ No newline at end of file diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/input_meta.py b/graph_net/paddle_samples/vision/squeezenet1_1/input_meta.py new file mode 100644 index 000000000..b9d94d068 --- /dev/null +++ b/graph_net/paddle_samples/vision/squeezenet1_1/input_meta.py @@ -0,0 +1,7 @@ +# Input metadata for SqueezeNet 1.1 +input_meta = { + "inputs": { + "shape": [1, 3, 224, 224], + "dtype": "float32" + } +} diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/paddle_samples/vision/squeezenet1_1/model.py new file mode 100644 index 000000000..429f3431e --- /dev/null +++ b/graph_net/paddle_samples/vision/squeezenet1_1/model.py @@ -0,0 +1,22 @@ +import paddle +from paddle.vision.models import squeezenet1_1 + +class GraphModule(paddle.nn.Layer): + def __init__(self): + super().__init__() + self.model = squeezenet1_1(pretrained=False) + + def forward(self, *args, **kwargs): + # 1. Try to get from positional args + # 2. Try to get from kwargs with common names + # 3. If all else fails, take the first value in kwargs dictionary + if args: + x = args[0] + elif "inputs" in kwargs: + x = kwargs["inputs"] + elif kwargs: + x = list(kwargs.values())[0] + else: + raise ValueError("No input tensor found in forward arguments") + + return self.model(x) diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json b/graph_net/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json new file mode 100644 index 000000000..8cdf0fc0b --- /dev/null +++ b/graph_net/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json @@ -0,0 +1,221 @@ +{ + (%0) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32> + (%1) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32> + (%2) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%3) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> + (%4) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%5) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> + (%6) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%7) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32> + (%8) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%9) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> + (%10) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> + (%11) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> + (%12) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%13) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32> + (%14) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%15) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> + (%16) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%17) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> + (%18) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> + (%19) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32> + (%20) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%21) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> + (%22) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> + (%23) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> + (%24) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> + (%25) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32> + (%26) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%27) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> + (%28) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%29) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> + (%30) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> + (%31) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32> + (%32) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%33) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> + (%34) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> + (%35) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> + (%36) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> + (%37) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32> + (%38) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%39) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> + (%40) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%41) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> + (%42) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> + (%43) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32> + (%44) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%45) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> + (%46) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%47) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> + (%48) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> + (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> + (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> + (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> + (%52) = "pd_op.data" () {dtype:float32,name:"inputs",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> + (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> + (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%56) = "pd_op.add" (%53, %55) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32> + (%57) = "pd_op.relu" (%56) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32> + (%58) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D/",value:[3,3]} : () -> tensor<2xi64> + (%59) = "pd_op.pool2d" (%57, %58) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D/"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32> + (%60) = "pd_op.conv2d" (%59, %49) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32> + (%61) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%62) = "pd_op.reshape" (%48, %61) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> + (%63) = "pd_op.add" (%60, %62) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> + (%64) = "pd_op.relu" (%63) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> + (%65) = "pd_op.conv2d" (%64, %47) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> + (%66) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%67) = "pd_op.reshape" (%46, %66) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%68) = "pd_op.add" (%65, %67) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%69) = "pd_op.relu" (%68) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%70) = "pd_op.conv2d" (%64, %45) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> + (%71) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%72) = "pd_op.reshape" (%44, %71) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%73) = "pd_op.add" (%70, %72) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%74) = "pd_op.relu" (%73) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%75) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/",value:1} : () -> tensor<1xi32> + (%76) = "builtin.combine" (%69, %74) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] + (%77) = "pd_op.concat" (%76, %75) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> + (%78) = "pd_op.conv2d" (%77, %43) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32> + (%79) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%80) = "pd_op.reshape" (%42, %79) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> + (%81) = "pd_op.add" (%78, %80) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> + (%82) = "pd_op.relu" (%81) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> + (%83) = "pd_op.conv2d" (%82, %41) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> + (%84) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%85) = "pd_op.reshape" (%40, %84) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%86) = "pd_op.add" (%83, %85) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%87) = "pd_op.relu" (%86) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%88) = "pd_op.conv2d" (%82, %39) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> + (%89) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%90) = "pd_op.reshape" (%38, %89) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%91) = "pd_op.add" (%88, %90) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> + (%92) = "pd_op.relu" (%91) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> + (%93) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/",value:1} : () -> tensor<1xi32> + (%94) = "builtin.combine" (%87, %92) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] + (%95) = "pd_op.concat" (%94, %93) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> + (%96) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_1/",value:[3,3]} : () -> tensor<2xi64> + (%97) = "pd_op.pool2d" (%95, %96) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_1/"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32> + (%98) = "pd_op.conv2d" (%97, %37) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32> + (%99) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%100) = "pd_op.reshape" (%36, %99) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> + (%101) = "pd_op.add" (%98, %100) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> + (%102) = "pd_op.relu" (%101) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> + (%103) = "pd_op.conv2d" (%102, %35) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> + (%104) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%105) = "pd_op.reshape" (%34, %104) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%106) = "pd_op.add" (%103, %105) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%107) = "pd_op.relu" (%106) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%108) = "pd_op.conv2d" (%102, %33) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> + (%109) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%110) = "pd_op.reshape" (%32, %109) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%111) = "pd_op.add" (%108, %110) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%112) = "pd_op.relu" (%111) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%113) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/",value:1} : () -> tensor<1xi32> + (%114) = "builtin.combine" (%107, %112) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] + (%115) = "pd_op.concat" (%114, %113) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> + (%116) = "pd_op.conv2d" (%115, %31) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32> + (%117) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%118) = "pd_op.reshape" (%30, %117) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> + (%119) = "pd_op.add" (%116, %118) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> + (%120) = "pd_op.relu" (%119) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> + (%121) = "pd_op.conv2d" (%120, %29) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> + (%122) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%123) = "pd_op.reshape" (%28, %122) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%124) = "pd_op.add" (%121, %123) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%125) = "pd_op.relu" (%124) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%126) = "pd_op.conv2d" (%120, %27) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> + (%127) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%128) = "pd_op.reshape" (%26, %127) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> + (%129) = "pd_op.add" (%126, %128) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> + (%130) = "pd_op.relu" (%129) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> + (%131) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/",value:1} : () -> tensor<1xi32> + (%132) = "builtin.combine" (%125, %130) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] + (%133) = "pd_op.concat" (%132, %131) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> + (%134) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_2/",value:[3,3]} : () -> tensor<2xi64> + (%135) = "pd_op.pool2d" (%133, %134) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_2/"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32> + (%136) = "pd_op.conv2d" (%135, %25) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32> + (%137) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%138) = "pd_op.reshape" (%24, %137) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> + (%139) = "pd_op.add" (%136, %138) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> + (%140) = "pd_op.relu" (%139) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> + (%141) = "pd_op.conv2d" (%140, %23) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> + (%142) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%143) = "pd_op.reshape" (%22, %142) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%144) = "pd_op.add" (%141, %143) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%145) = "pd_op.relu" (%144) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%146) = "pd_op.conv2d" (%140, %21) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> + (%147) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%148) = "pd_op.reshape" (%20, %147) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%149) = "pd_op.add" (%146, %148) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%150) = "pd_op.relu" (%149) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%151) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/",value:1} : () -> tensor<1xi32> + (%152) = "builtin.combine" (%145, %150) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] + (%153) = "pd_op.concat" (%152, %151) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> + (%154) = "pd_op.conv2d" (%153, %19) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32> + (%155) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%156) = "pd_op.reshape" (%18, %155) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> + (%157) = "pd_op.add" (%154, %156) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> + (%158) = "pd_op.relu" (%157) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> + (%159) = "pd_op.conv2d" (%158, %17) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> + (%160) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%161) = "pd_op.reshape" (%16, %160) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%162) = "pd_op.add" (%159, %161) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%163) = "pd_op.relu" (%162) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%164) = "pd_op.conv2d" (%158, %15) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> + (%165) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%166) = "pd_op.reshape" (%14, %165) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> + (%167) = "pd_op.add" (%164, %166) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> + (%168) = "pd_op.relu" (%167) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> + (%169) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/",value:1} : () -> tensor<1xi32> + (%170) = "builtin.combine" (%163, %168) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] + (%171) = "pd_op.concat" (%170, %169) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> + (%172) = "pd_op.conv2d" (%171, %13) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32> + (%173) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%174) = "pd_op.reshape" (%12, %173) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%175) = "pd_op.add" (%172, %174) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> + (%176) = "pd_op.relu" (%175) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> + (%177) = "pd_op.conv2d" (%176, %11) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> + (%178) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%179) = "pd_op.reshape" (%10, %178) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%180) = "pd_op.add" (%177, %179) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%181) = "pd_op.relu" (%180) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%182) = "pd_op.conv2d" (%176, %9) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> + (%183) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%184) = "pd_op.reshape" (%8, %183) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%185) = "pd_op.add" (%182, %184) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%186) = "pd_op.relu" (%185) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%187) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/",value:1} : () -> tensor<1xi32> + (%188) = "builtin.combine" (%181, %186) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] + (%189) = "pd_op.concat" (%188, %187) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> + (%190) = "pd_op.conv2d" (%189, %7) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32> + (%191) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%192) = "pd_op.reshape" (%6, %191) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> + (%193) = "pd_op.add" (%190, %192) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> + (%194) = "pd_op.relu" (%193) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> + (%195) = "pd_op.conv2d" (%194, %5) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> + (%196) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%197) = "pd_op.reshape" (%4, %196) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%198) = "pd_op.add" (%195, %197) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%199) = "pd_op.relu" (%198) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%200) = "pd_op.conv2d" (%194, %3) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> + (%201) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%202) = "pd_op.reshape" (%2, %201) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> + (%203) = "pd_op.add" (%200, %202) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> + (%204) = "pd_op.relu" (%203) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> + (%205) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/",value:1} : () -> tensor<1xi32> + (%206) = "builtin.combine" (%199, %204) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] + (%207) = "pd_op.concat" (%206, %205) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> + (%208) = "pd_op.full" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/Dropout/",value:0.5} : () -> tensor<1xf32> + (%209, %210) = "pd_op.dropout" (%207, <>, %208) {fix_seed:false,is_test:false,mode:"downgrade_in_infer",seed:0,stop_gradient:[false,false],struct_name:"/SqueezeNet/Dropout/"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8> + (%211) = "pd_op.conv2d" (%209, %1) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32> + (%212) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D_1/",value:[1,-1,1,1]} : () -> tensor<4xi64> + (%213) = "pd_op.reshape" (%0, %212) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32> + (%214) = "pd_op.add" (%211, %213) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32> + (%215) = "pd_op.relu" (%214) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32> + (%216) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/",value:[1,1]} : () -> tensor<2xi64> + (%217) = "pd_op.pool2d" (%215, %216) {adaptive:true,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"avg",stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32> + (%218) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/",value:[2,3]} : () -> tensor<2xi64> + (%219) = "pd_op.squeeze" (%217, %218) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32> +} diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/weight_meta.py b/graph_net/paddle_samples/vision/squeezenet1_1/weight_meta.py new file mode 100644 index 000000000..80606a5fb --- /dev/null +++ b/graph_net/paddle_samples/vision/squeezenet1_1/weight_meta.py @@ -0,0 +1,2 @@ +# Weight metadata for SqueezeNet 1.1 +weight_meta = {} diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index b3f74a8dd..bc3e1f96c 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -14,13 +14,12 @@ def extract_squeezenet(): model = squeezenet1_1(pretrained=False) model(inputs) - # 使用绝对路径，防止 FileNotFoundError base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + # Updated save path to the new directory structure save_path = os.path.join( - base_dir, "samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json" + base_dir, "paddle_samples/vision/squeezenet1_1/squeezenet1_1.json" ) - # 确保目录存在 os.makedirs(os.path.dirname(save_path), exist_ok=True) with open(save_path, "w") as f: From 85f9fdce3974ac16ba57a8a6442fe60b9b318d1f Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Fri, 6 Mar 2026 17:00:17 +0800 Subject: [PATCH 08/12] refactor: sync final graph hash and align directory to PaddleX --- .../vision/squeezenet1_1/graph_hash.txt | 1 - .../vision/squeezenet1_1/model.py | 22 -- .../vision/squeezenet1_1/__init__.py | 0 .../vision/squeezenet1_1/graph_hash.txt | 1 - .../vision/squeezenet1_1/input_meta.py | 3 - .../vision/squeezenet1_1/model.py | 13 -- .../vision/squeezenet1_1/squeezenet1_1.json | 221 ------------------ .../vision/squeezenet1_1/weight_meta.py | 3 - graph_net/tests/test_squeezenet1_1_extract.py | 8 +- .../PaddleX}/squeezenet1_1/__init__.py | 0 .../PaddleX/squeezenet1_1/graph_hash.txt | 1 + .../PaddleX}/squeezenet1_1/input_meta.py | 0 paddle_samples/PaddleX/squeezenet1_1/model.py | 24 ++ .../PaddleX}/squeezenet1_1/squeezenet1_1.json | 0 .../PaddleX}/squeezenet1_1/weight_meta.py | 0 15 files changed, 28 insertions(+), 269 deletions(-) delete mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt delete mode 100644 graph_net/paddle_samples/vision/squeezenet1_1/model.py delete mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/__init__.py delete mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt delete mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py delete mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py delete mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json delete mode 100644 graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py rename {graph_net/paddle_samples/vision => paddle_samples/PaddleX}/squeezenet1_1/__init__.py (100%) create mode 100644 paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt rename {graph_net/paddle_samples/vision => paddle_samples/PaddleX}/squeezenet1_1/input_meta.py (100%) create mode 100644 paddle_samples/PaddleX/squeezenet1_1/model.py rename {graph_net/paddle_samples/vision => paddle_samples/PaddleX}/squeezenet1_1/squeezenet1_1.json (100%) rename {graph_net/paddle_samples/vision => paddle_samples/PaddleX}/squeezenet1_1/weight_meta.py (100%) diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt deleted file mode 100644 index 03302b77a..000000000 --- a/graph_net/paddle_samples/vision/squeezenet1_1/graph_hash.txt +++ /dev/null @@ -1 +0,0 @@ -e4f3a5c6f15919d2254bbb54f324e06f176251076e5685054924329e7d189b38 \ No newline at end of file diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/paddle_samples/vision/squeezenet1_1/model.py deleted file mode 100644 index 429f3431e..000000000 --- a/graph_net/paddle_samples/vision/squeezenet1_1/model.py +++ /dev/null @@ -1,22 +0,0 @@ -import paddle -from paddle.vision.models import squeezenet1_1 - -class GraphModule(paddle.nn.Layer): - def __init__(self): - super().__init__() - self.model = squeezenet1_1(pretrained=False) - - def forward(self, *args, **kwargs): - # 1. Try to get from positional args - # 2. Try to get from kwargs with common names - # 3. If all else fails, take the first value in kwargs dictionary - if args: - x = args[0] - elif "inputs" in kwargs: - x = kwargs["inputs"] - elif kwargs: - x = list(kwargs.values())[0] - else: - raise ValueError("No input tensor found in forward arguments") - - return self.model(x) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/__init__.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/__init__.py deleted file mode 100644 index e69de29bb..000000000 diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt b/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt deleted file mode 100644 index 5f2ab450b..000000000 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/graph_hash.txt +++ /dev/null @@ -1 +0,0 @@ -fe50e21a3d942119b84131723149ca314a6ca2dc77fdf4fde773542e4abd4675 \ No newline at end of file diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py deleted file mode 100644 index e8938c68a..000000000 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/input_meta.py +++ /dev/null @@ -1,3 +0,0 @@ -import paddle - -input_meta = {"inputs": {"shape": [1, 3, 224, 224], "dtype": "float32"}} diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py deleted file mode 100644 index 8965ec16d..000000000 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/model.py +++ /dev/null @@ -1,13 +0,0 @@ -import paddle -from paddle.vision.models import squeezenet1_1 - - -class GraphModule(paddle.nn.Layer): - def __init__(self): - super().__init__() - self.model = squeezenet1_1(pretrained=False) - - def forward(self, *args, **kwargs): - # 兼容性抓取：优先抓取位置参数第一个，或者关键字参数名为 'inputs' 的 - x = args[0] if args else kwargs.get("inputs") - return self.model(x) diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json b/graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json deleted file mode 100644 index 8cdf0fc0b..000000000 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json +++ /dev/null @@ -1,221 +0,0 @@ -{ - (%0) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32> - (%1) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32> - (%2) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%3) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> - (%4) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%5) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> - (%6) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%7) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32> - (%8) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%9) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> - (%10) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%11) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> - (%12) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%13) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32> - (%14) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%15) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> - (%16) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%17) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> - (%18) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> - (%19) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32> - (%20) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%21) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> - (%22) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%23) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> - (%24) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> - (%25) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32> - (%26) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%27) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> - (%28) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%29) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> - (%30) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> - (%31) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32> - (%32) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%33) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> - (%34) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%35) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> - (%36) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> - (%37) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32> - (%38) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%39) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> - (%40) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%41) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> - (%42) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> - (%43) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32> - (%44) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%45) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> - (%46) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%47) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> - (%48) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> - (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> - (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> - (%52) = "pd_op.data" () {dtype:float32,name:"inputs",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> - (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> - (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%56) = "pd_op.add" (%53, %55) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32> - (%57) = "pd_op.relu" (%56) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32> - (%58) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D/",value:[3,3]} : () -> tensor<2xi64> - (%59) = "pd_op.pool2d" (%57, %58) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D/"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32> - (%60) = "pd_op.conv2d" (%59, %49) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32> - (%61) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%62) = "pd_op.reshape" (%48, %61) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> - (%63) = "pd_op.add" (%60, %62) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> - (%64) = "pd_op.relu" (%63) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> - (%65) = "pd_op.conv2d" (%64, %47) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> - (%66) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%67) = "pd_op.reshape" (%46, %66) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%68) = "pd_op.add" (%65, %67) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%69) = "pd_op.relu" (%68) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%70) = "pd_op.conv2d" (%64, %45) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> - (%71) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%72) = "pd_op.reshape" (%44, %71) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%73) = "pd_op.add" (%70, %72) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%74) = "pd_op.relu" (%73) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%75) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/",value:1} : () -> tensor<1xi32> - (%76) = "builtin.combine" (%69, %74) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] - (%77) = "pd_op.concat" (%76, %75) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> - (%78) = "pd_op.conv2d" (%77, %43) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32> - (%79) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%80) = "pd_op.reshape" (%42, %79) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> - (%81) = "pd_op.add" (%78, %80) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> - (%82) = "pd_op.relu" (%81) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> - (%83) = "pd_op.conv2d" (%82, %41) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> - (%84) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%85) = "pd_op.reshape" (%40, %84) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%86) = "pd_op.add" (%83, %85) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%87) = "pd_op.relu" (%86) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%88) = "pd_op.conv2d" (%82, %39) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> - (%89) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%90) = "pd_op.reshape" (%38, %89) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%91) = "pd_op.add" (%88, %90) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%92) = "pd_op.relu" (%91) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%93) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/",value:1} : () -> tensor<1xi32> - (%94) = "builtin.combine" (%87, %92) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] - (%95) = "pd_op.concat" (%94, %93) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> - (%96) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_1/",value:[3,3]} : () -> tensor<2xi64> - (%97) = "pd_op.pool2d" (%95, %96) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_1/"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32> - (%98) = "pd_op.conv2d" (%97, %37) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32> - (%99) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%100) = "pd_op.reshape" (%36, %99) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> - (%101) = "pd_op.add" (%98, %100) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> - (%102) = "pd_op.relu" (%101) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> - (%103) = "pd_op.conv2d" (%102, %35) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> - (%104) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%105) = "pd_op.reshape" (%34, %104) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%106) = "pd_op.add" (%103, %105) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%107) = "pd_op.relu" (%106) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%108) = "pd_op.conv2d" (%102, %33) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> - (%109) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%110) = "pd_op.reshape" (%32, %109) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%111) = "pd_op.add" (%108, %110) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%112) = "pd_op.relu" (%111) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%113) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/",value:1} : () -> tensor<1xi32> - (%114) = "builtin.combine" (%107, %112) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] - (%115) = "pd_op.concat" (%114, %113) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> - (%116) = "pd_op.conv2d" (%115, %31) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32> - (%117) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%118) = "pd_op.reshape" (%30, %117) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> - (%119) = "pd_op.add" (%116, %118) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> - (%120) = "pd_op.relu" (%119) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> - (%121) = "pd_op.conv2d" (%120, %29) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> - (%122) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%123) = "pd_op.reshape" (%28, %122) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%124) = "pd_op.add" (%121, %123) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%125) = "pd_op.relu" (%124) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%126) = "pd_op.conv2d" (%120, %27) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> - (%127) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%128) = "pd_op.reshape" (%26, %127) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%129) = "pd_op.add" (%126, %128) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%130) = "pd_op.relu" (%129) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%131) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/",value:1} : () -> tensor<1xi32> - (%132) = "builtin.combine" (%125, %130) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] - (%133) = "pd_op.concat" (%132, %131) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> - (%134) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_2/",value:[3,3]} : () -> tensor<2xi64> - (%135) = "pd_op.pool2d" (%133, %134) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_2/"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32> - (%136) = "pd_op.conv2d" (%135, %25) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32> - (%137) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%138) = "pd_op.reshape" (%24, %137) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> - (%139) = "pd_op.add" (%136, %138) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> - (%140) = "pd_op.relu" (%139) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> - (%141) = "pd_op.conv2d" (%140, %23) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> - (%142) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%143) = "pd_op.reshape" (%22, %142) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%144) = "pd_op.add" (%141, %143) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%145) = "pd_op.relu" (%144) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%146) = "pd_op.conv2d" (%140, %21) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> - (%147) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%148) = "pd_op.reshape" (%20, %147) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%149) = "pd_op.add" (%146, %148) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%150) = "pd_op.relu" (%149) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%151) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/",value:1} : () -> tensor<1xi32> - (%152) = "builtin.combine" (%145, %150) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] - (%153) = "pd_op.concat" (%152, %151) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> - (%154) = "pd_op.conv2d" (%153, %19) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32> - (%155) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%156) = "pd_op.reshape" (%18, %155) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> - (%157) = "pd_op.add" (%154, %156) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> - (%158) = "pd_op.relu" (%157) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> - (%159) = "pd_op.conv2d" (%158, %17) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> - (%160) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%161) = "pd_op.reshape" (%16, %160) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%162) = "pd_op.add" (%159, %161) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%163) = "pd_op.relu" (%162) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%164) = "pd_op.conv2d" (%158, %15) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> - (%165) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%166) = "pd_op.reshape" (%14, %165) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%167) = "pd_op.add" (%164, %166) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%168) = "pd_op.relu" (%167) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%169) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/",value:1} : () -> tensor<1xi32> - (%170) = "builtin.combine" (%163, %168) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] - (%171) = "pd_op.concat" (%170, %169) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> - (%172) = "pd_op.conv2d" (%171, %13) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32> - (%173) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%174) = "pd_op.reshape" (%12, %173) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%175) = "pd_op.add" (%172, %174) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> - (%176) = "pd_op.relu" (%175) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> - (%177) = "pd_op.conv2d" (%176, %11) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> - (%178) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%179) = "pd_op.reshape" (%10, %178) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%180) = "pd_op.add" (%177, %179) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%181) = "pd_op.relu" (%180) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%182) = "pd_op.conv2d" (%176, %9) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> - (%183) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%184) = "pd_op.reshape" (%8, %183) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%185) = "pd_op.add" (%182, %184) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%186) = "pd_op.relu" (%185) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%187) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/",value:1} : () -> tensor<1xi32> - (%188) = "builtin.combine" (%181, %186) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] - (%189) = "pd_op.concat" (%188, %187) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> - (%190) = "pd_op.conv2d" (%189, %7) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32> - (%191) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%192) = "pd_op.reshape" (%6, %191) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%193) = "pd_op.add" (%190, %192) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> - (%194) = "pd_op.relu" (%193) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> - (%195) = "pd_op.conv2d" (%194, %5) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> - (%196) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%197) = "pd_op.reshape" (%4, %196) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%198) = "pd_op.add" (%195, %197) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%199) = "pd_op.relu" (%198) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%200) = "pd_op.conv2d" (%194, %3) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> - (%201) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%202) = "pd_op.reshape" (%2, %201) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%203) = "pd_op.add" (%200, %202) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%204) = "pd_op.relu" (%203) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%205) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/",value:1} : () -> tensor<1xi32> - (%206) = "builtin.combine" (%199, %204) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] - (%207) = "pd_op.concat" (%206, %205) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> - (%208) = "pd_op.full" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/Dropout/",value:0.5} : () -> tensor<1xf32> - (%209, %210) = "pd_op.dropout" (%207, <>, %208) {fix_seed:false,is_test:false,mode:"downgrade_in_infer",seed:0,stop_gradient:[false,false],struct_name:"/SqueezeNet/Dropout/"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8> - (%211) = "pd_op.conv2d" (%209, %1) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32> - (%212) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D_1/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%213) = "pd_op.reshape" (%0, %212) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32> - (%214) = "pd_op.add" (%211, %213) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32> - (%215) = "pd_op.relu" (%214) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32> - (%216) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/",value:[1,1]} : () -> tensor<2xi64> - (%217) = "pd_op.pool2d" (%215, %216) {adaptive:true,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"avg",stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32> - (%218) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/",value:[2,3]} : () -> tensor<2xi64> - (%219) = "pd_op.squeeze" (%217, %218) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32> -} diff --git a/graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py b/graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py deleted file mode 100644 index 714737364..000000000 --- a/graph_net/samples/paddle_samples/vision/squeezenet1_1/weight_meta.py +++ /dev/null @@ -1,3 +0,0 @@ -import paddle - -weight_meta = {} diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index bc3e1f96c..2e8834ea5 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -2,7 +2,6 @@ import os from paddle.vision.models import squeezenet1_1 - def extract_squeezenet(): os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() @@ -14,10 +13,10 @@ def extract_squeezenet(): model = squeezenet1_1(pretrained=False) model(inputs) - base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) - # Updated save path to the new directory structure + # Correct path to the new root-level paddle_samples directory + base_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) save_path = os.path.join( - base_dir, "paddle_samples/vision/squeezenet1_1/squeezenet1_1.json" + base_dir, "paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json" ) os.makedirs(os.path.dirname(save_path), exist_ok=True) @@ -26,6 +25,5 @@ def extract_squeezenet(): f.write(str(main_program)) print(f"Extract success! Saved to: {save_path}") - if __name__ == "__main__": extract_squeezenet() diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/__init__.py b/paddle_samples/PaddleX/squeezenet1_1/__init__.py similarity index 100% rename from graph_net/paddle_samples/vision/squeezenet1_1/__init__.py rename to paddle_samples/PaddleX/squeezenet1_1/__init__.py diff --git a/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt b/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt new file mode 100644 index 000000000..23fae9dc6 --- /dev/null +++ b/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt @@ -0,0 +1 @@ +4e0086fc9594636c498a6818f79002a5a0dc6e2478a7ec4bf1fee2699988a167 \ No newline at end of file diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/input_meta.py b/paddle_samples/PaddleX/squeezenet1_1/input_meta.py similarity index 100% rename from graph_net/paddle_samples/vision/squeezenet1_1/input_meta.py rename to paddle_samples/PaddleX/squeezenet1_1/input_meta.py diff --git a/paddle_samples/PaddleX/squeezenet1_1/model.py b/paddle_samples/PaddleX/squeezenet1_1/model.py new file mode 100644 index 000000000..5d8a42947 --- /dev/null +++ b/paddle_samples/PaddleX/squeezenet1_1/model.py @@ -0,0 +1,24 @@ +import paddle +from paddle.vision.models import squeezenet1_1 + +class GraphModule(paddle.nn.Layer): + def __init__(self): + super().__init__() + self.model = squeezenet1_1(pretrained=False) + + def forward(self, *args, **kwargs): + # 1. Try to get from positional args + if args: + x = args[0] + # 2. Try to get from kwargs (looking for any Tensor) + else: + x = None + for val in kwargs.values(): + if isinstance(val, (paddle.Tensor, paddle.static.Variable)): + x = val + break + + if x is None: + raise ValueError(f"No input tensor found. args: {len(args)}, kwargs keys: {list(kwargs.keys())}") + + return self.model(x) diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json b/paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json similarity index 100% rename from graph_net/paddle_samples/vision/squeezenet1_1/squeezenet1_1.json rename to paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json diff --git a/graph_net/paddle_samples/vision/squeezenet1_1/weight_meta.py b/paddle_samples/PaddleX/squeezenet1_1/weight_meta.py similarity index 100% rename from graph_net/paddle_samples/vision/squeezenet1_1/weight_meta.py rename to paddle_samples/PaddleX/squeezenet1_1/weight_meta.py From 79972d2b98e8347eb2d4cb4fef676ac01b6a9846 Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Fri, 6 Mar 2026 17:11:58 +0800 Subject: [PATCH 09/12] refactor: final directory alignment, code formatting, and hash sync --- graph_net/tests/test_squeezenet1_1_extract.py | 6 +++++- .../PaddleX/squeezenet1_1/graph_hash.txt | 2 +- .../PaddleX/squeezenet1_1/input_meta.py | 7 +------ paddle_samples/PaddleX/squeezenet1_1/model.py | 21 +++++++++---------- 4 files changed, 17 insertions(+), 19 deletions(-) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index 2e8834ea5..7b4a94cb5 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -2,6 +2,7 @@ import os from paddle.vision.models import squeezenet1_1 + def extract_squeezenet(): os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() @@ -14,7 +15,9 @@ def extract_squeezenet(): model(inputs) # Correct path to the new root-level paddle_samples directory - base_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + base_dir = os.path.dirname( + os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + ) save_path = os.path.join( base_dir, "paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json" ) @@ -25,5 +28,6 @@ def extract_squeezenet(): f.write(str(main_program)) print(f"Extract success! Saved to: {save_path}") + if __name__ == "__main__": extract_squeezenet() diff --git a/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt b/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt index 23fae9dc6..87f414f90 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt +++ b/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt @@ -1 +1 @@ -4e0086fc9594636c498a6818f79002a5a0dc6e2478a7ec4bf1fee2699988a167 \ No newline at end of file +34d3e759910d328ffe6f3c66943f08ab8df60b585bb3237f08eedc0c8baecf7d \ No newline at end of file diff --git a/paddle_samples/PaddleX/squeezenet1_1/input_meta.py b/paddle_samples/PaddleX/squeezenet1_1/input_meta.py index b9d94d068..ccbcf77da 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/input_meta.py +++ b/paddle_samples/PaddleX/squeezenet1_1/input_meta.py @@ -1,7 +1,2 @@ # Input metadata for SqueezeNet 1.1 -input_meta = { - "inputs": { - "shape": [1, 3, 224, 224], - "dtype": "float32" - } -} +input_meta = {"x": {"shape": [1, 3, 224, 224], "dtype": "float32"}} diff --git a/paddle_samples/PaddleX/squeezenet1_1/model.py b/paddle_samples/PaddleX/squeezenet1_1/model.py index 5d8a42947..a95993b24 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/model.py +++ b/paddle_samples/PaddleX/squeezenet1_1/model.py @@ -1,24 +1,23 @@ import paddle from paddle.vision.models import squeezenet1_1 + class GraphModule(paddle.nn.Layer): def __init__(self): super().__init__() self.model = squeezenet1_1(pretrained=False) - def forward(self, *args, **kwargs): - # 1. Try to get from positional args - if args: - x = args[0] - # 2. Try to get from kwargs (looking for any Tensor) - else: - x = None + def forward(self, x=None, **kwargs): + # If x is not passed directly, try to find any tensor in kwargs + if x is None: for val in kwargs.values(): if isinstance(val, (paddle.Tensor, paddle.static.Variable)): x = val break - - if x is None: - raise ValueError(f"No input tensor found. args: {len(args)}, kwargs keys: {list(kwargs.keys())}") - + + if x is None: + raise ValueError( + f"No input tensor found. kwargs keys: {list(kwargs.keys())}" + ) + return self.model(x) From 05912dfecc4402f75f2dbf7396bd96595b39285e Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Fri, 6 Mar 2026 23:01:05 +0800 Subject: [PATCH 10/12] fix: final sample validation success for squeezenet1_1 in PaddleX --- graph_net/tests/test_squeezenet1_1_extract.py | 7 +++++-- .../PaddleX/squeezenet1_1/graph_hash.txt | 2 +- .../PaddleX/squeezenet1_1/input_meta.py | 13 ++++++++++++- paddle_samples/PaddleX/squeezenet1_1/model.py | 19 ++++++++++++------- .../PaddleX/squeezenet1_1/squeezenet1_1.json | 2 +- 5 files changed, 31 insertions(+), 12 deletions(-) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index 7b4a94cb5..7a4f23cd8 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -4,17 +4,20 @@ def extract_squeezenet(): + # Enable PIR and static mode os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() + main_program = paddle.static.Program() with paddle.static.program_guard(main_program): + # 关键点：name 必须等于 "image" inputs = paddle.static.data( - name="inputs", shape=[1, 3, 224, 224], dtype="float32" + name="image", shape=[1, 3, 224, 224], dtype="float32" ) model = squeezenet1_1(pretrained=False) model(inputs) - # Correct path to the new root-level paddle_samples directory + # Define save path to root-level paddle_samples base_dir = os.path.dirname( os.path.dirname(os.path.dirname(os.path.abspath(__file__))) ) diff --git a/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt b/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt index 87f414f90..18b6e5171 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt +++ b/paddle_samples/PaddleX/squeezenet1_1/graph_hash.txt @@ -1 +1 @@ -34d3e759910d328ffe6f3c66943f08ab8df60b585bb3237f08eedc0c8baecf7d \ No newline at end of file +a87bc38868b688b562b67634fb432eab7051fff838290f80ec278d02c9391a80 \ No newline at end of file diff --git a/paddle_samples/PaddleX/squeezenet1_1/input_meta.py b/paddle_samples/PaddleX/squeezenet1_1/input_meta.py index ccbcf77da..d41e0d9b7 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/input_meta.py +++ b/paddle_samples/PaddleX/squeezenet1_1/input_meta.py @@ -1,2 +1,13 @@ # Input metadata for SqueezeNet 1.1 -input_meta = {"x": {"shape": [1, 3, 224, 224], "dtype": "float32"}} + + +# This follows the style of existing samples in the repo +class Program_input_tensor_image: + name = "image" + shape = [1, 3, 224, 224] + dtype = "float32" + data = None + + +# The validation script needs this dict to match with model.forward(**state_dict) +input_meta = {"image": {"shape": [1, 3, 224, 224], "dtype": "float32"}} diff --git a/paddle_samples/PaddleX/squeezenet1_1/model.py b/paddle_samples/PaddleX/squeezenet1_1/model.py index a95993b24..946875a0d 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/model.py +++ b/paddle_samples/PaddleX/squeezenet1_1/model.py @@ -7,17 +7,22 @@ def __init__(self): super().__init__() self.model = squeezenet1_1(pretrained=False) - def forward(self, x=None, **kwargs): - # If x is not passed directly, try to find any tensor in kwargs - if x is None: + def forward(self, *args, **kwargs): + # 1. Try to get tensor from positional arguments + if args: + x = args[0] + # 2. Try to get tensor from keyword arguments + else: + x = None for val in kwargs.values(): if isinstance(val, (paddle.Tensor, paddle.static.Variable)): x = val break - if x is None: - raise ValueError( - f"No input tensor found. kwargs keys: {list(kwargs.keys())}" - ) + if x is None: + # Log keys for debugging in CI if it fails again + raise ValueError( + f"No input tensor found. args_len: {len(args)}, kwargs_keys: {list(kwargs.keys())}" + ) return self.model(x) diff --git a/paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json b/paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json index 8cdf0fc0b..98b405b3c 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json +++ b/paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json @@ -51,7 +51,7 @@ (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> - (%52) = "pd_op.data" () {dtype:float32,name:"inputs",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> + (%52) = "pd_op.data" () {dtype:float32,name:"image",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> From f02489c0048f7b89afe4430975bd5af31771117a Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Mon, 9 Mar 2026 15:05:57 +0800 Subject: [PATCH 11/12] style: final codestyle fix and rename to graph_net.json --- graph_net/tests/test_squeezenet1_1_extract.py | 24 +++++++++---------- .../{squeezenet1_1.json => graph_net.json} | 0 2 files changed, 12 insertions(+), 12 deletions(-) rename paddle_samples/PaddleX/squeezenet1_1/{squeezenet1_1.json => graph_net.json} (100%) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index 7a4f23cd8..da36cf56d 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -4,32 +4,32 @@ def extract_squeezenet(): - # Enable PIR and static mode + # 1. 环境准备 os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() + # 2. 捕获计算图 main_program = paddle.static.Program() with paddle.static.program_guard(main_program): - # 关键点：name 必须等于 "image" + # 统一使用 'image' 作为输入名，确保与 input_meta.py 一致 inputs = paddle.static.data( name="image", shape=[1, 3, 224, 224], dtype="float32" ) model = squeezenet1_1(pretrained=False) model(inputs) - # Define save path to root-level paddle_samples - base_dir = os.path.dirname( - os.path.dirname(os.path.dirname(os.path.abspath(__file__))) - ) - save_path = os.path.join( - base_dir, "paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json" - ) - - os.makedirs(os.path.dirname(save_path), exist_ok=True) + # 3. 强制指定绝对路径和标准 graph_net.json + current_file_path = os.path.abspath(__file__) + project_root = os.path.dirname(os.path.dirname(os.path.dirname(current_file_path))) + target_dir = os.path.join(project_root, "paddle_samples/PaddleX/squeezenet1_1") + save_path = os.path.join(target_dir, "graph_net.json") + # 4. 确保目录存在并写入 + os.makedirs(target_dir, exist_ok=True) with open(save_path, "w") as f: f.write(str(main_program)) - print(f"Extract success! Saved to: {save_path}") + + print(f"✅ 提取成功！标准文件已生成至: {save_path}") if __name__ == "__main__": diff --git a/paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json b/paddle_samples/PaddleX/squeezenet1_1/graph_net.json similarity index 100% rename from paddle_samples/PaddleX/squeezenet1_1/squeezenet1_1.json rename to paddle_samples/PaddleX/squeezenet1_1/graph_net.json From 26e12b66f8fea3591a3ac4c183ed2b8ec6e9ff36 Mon Sep 17 00:00:00 2001 From: Carousel126 Date: Mon, 9 Mar 2026 15:31:25 +0800 Subject: [PATCH 12/12] style: resolve JSONDecodeError and enforce black codestyle for squeezenet1_1 --- graph_net/tests/test_squeezenet1_1_extract.py | 19 +- .../PaddleX/squeezenet1_1/graph_net.json | 223 +----------------- 2 files changed, 15 insertions(+), 227 deletions(-) diff --git a/graph_net/tests/test_squeezenet1_1_extract.py b/graph_net/tests/test_squeezenet1_1_extract.py index da36cf56d..2280d03e0 100644 --- a/graph_net/tests/test_squeezenet1_1_extract.py +++ b/graph_net/tests/test_squeezenet1_1_extract.py @@ -1,35 +1,40 @@ import paddle import os +import json from paddle.vision.models import squeezenet1_1 def extract_squeezenet(): - # 1. 环境准备 + # 1. Environment setup os.environ["FLAGS_enable_pir_api"] = "1" paddle.enable_static() - # 2. 捕获计算图 + # 2. Capture computation graph main_program = paddle.static.Program() with paddle.static.program_guard(main_program): - # 统一使用 'image' 作为输入名，确保与 input_meta.py 一致 inputs = paddle.static.data( name="image", shape=[1, 3, 224, 224], dtype="float32" ) model = squeezenet1_1(pretrained=False) model(inputs) - # 3. 强制指定绝对路径和标准 graph_net.json + # 3. Get absolute save path current_file_path = os.path.abspath(__file__) project_root = os.path.dirname(os.path.dirname(os.path.dirname(current_file_path))) target_dir = os.path.join(project_root, "paddle_samples/PaddleX/squeezenet1_1") save_path = os.path.join(target_dir, "graph_net.json") - # 4. 确保目录存在并写入 + # 4. Standardize format: Convert program to a valid JSON string + # We wrap it in a dictionary to ensure valid JSON structure with double quotes + program_content = str(main_program) + json_data = {"protocol": "PIR", "program_desc": program_content} + + # 5. Write to file using json.dump (this enforces double quotes for keys) os.makedirs(target_dir, exist_ok=True) with open(save_path, "w") as f: - f.write(str(main_program)) + json.dump(json_data, f, indent=4) - print(f"✅ 提取成功！标准文件已生成至: {save_path}") + print(f"Extraction successful! Standard JSON generated at: {save_path}") if __name__ == "__main__": diff --git a/paddle_samples/PaddleX/squeezenet1_1/graph_net.json b/paddle_samples/PaddleX/squeezenet1_1/graph_net.json index 98b405b3c..6b77276be 100644 --- a/paddle_samples/PaddleX/squeezenet1_1/graph_net.json +++ b/paddle_samples/PaddleX/squeezenet1_1/graph_net.json @@ -1,221 +1,4 @@ { - (%0) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32> - (%1) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_25.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32> - (%2) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%3) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_24.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> - (%4) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%5) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_23.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> - (%6) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%7) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_22.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32> - (%8) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%9) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_21.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32> - (%10) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32> - (%11) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_20.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32> - (%12) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%13) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_19.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32> - (%14) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%15) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_18.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> - (%16) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%17) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_17.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> - (%18) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> - (%19) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_16.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32> - (%20) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%21) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_15.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32> - (%22) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32> - (%23) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_14.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32> - (%24) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32> - (%25) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_13.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32> - (%26) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%27) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_12.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> - (%28) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%29) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_11.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> - (%30) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> - (%31) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_10.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32> - (%32) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%33) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_9.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32> - (%34) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32> - (%35) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_8.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32> - (%36) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32> - (%37) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_7.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32> - (%38) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%39) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_6.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> - (%40) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%41) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_5.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> - (%42) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> - (%43) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_4.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32> - (%44) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%45) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_3.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32> - (%46) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%47) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_2.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32> - (%48) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32> - (%49) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_1.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32> - (%50) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.b_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32> - (%51) = "builtin.parameter" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:"conv2d_0.w_0",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32> - (%52) = "pd_op.data" () {dtype:float32,name:"image",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32> - (%53) = "pd_op.conv2d" (%52, %51) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32> - (%54) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%55) = "pd_op.reshape" (%50, %54) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%56) = "pd_op.add" (%53, %55) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D/"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32> - (%57) = "pd_op.relu" (%56) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32> - (%58) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D/",value:[3,3]} : () -> tensor<2xi64> - (%59) = "pd_op.pool2d" (%57, %58) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D/"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32> - (%60) = "pd_op.conv2d" (%59, %49) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32> - (%61) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%62) = "pd_op.reshape" (%48, %61) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> - (%63) = "pd_op.add" (%60, %62) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> - (%64) = "pd_op.relu" (%63) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> - (%65) = "pd_op.conv2d" (%64, %47) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> - (%66) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%67) = "pd_op.reshape" (%46, %66) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%68) = "pd_op.add" (%65, %67) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%69) = "pd_op.relu" (%68) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%70) = "pd_op.conv2d" (%64, %45) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> - (%71) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%72) = "pd_op.reshape" (%44, %71) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%73) = "pd_op.add" (%70, %72) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%74) = "pd_op.relu" (%73) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%75) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire/",value:1} : () -> tensor<1xi32> - (%76) = "builtin.combine" (%69, %74) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] - (%77) = "pd_op.concat" (%76, %75) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> - (%78) = "pd_op.conv2d" (%77, %43) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32> - (%79) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%80) = "pd_op.reshape" (%42, %79) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32> - (%81) = "pd_op.add" (%78, %80) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32> - (%82) = "pd_op.relu" (%81) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv/"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32> - (%83) = "pd_op.conv2d" (%82, %41) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32> - (%84) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%85) = "pd_op.reshape" (%40, %84) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%86) = "pd_op.add" (%83, %85) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%87) = "pd_op.relu" (%86) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_1/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%88) = "pd_op.conv2d" (%82, %39) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32> - (%89) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%90) = "pd_op.reshape" (%38, %89) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%91) = "pd_op.add" (%88, %90) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32> - (%92) = "pd_op.relu" (%91) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/MakeFireConv_2/"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32> - (%93) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_1/",value:1} : () -> tensor<1xi32> - (%94) = "builtin.combine" (%87, %92) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>] - (%95) = "pd_op.concat" (%94, %93) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_1/"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32> - (%96) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_1/",value:[3,3]} : () -> tensor<2xi64> - (%97) = "pd_op.pool2d" (%95, %96) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_1/"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32> - (%98) = "pd_op.conv2d" (%97, %37) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32> - (%99) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%100) = "pd_op.reshape" (%36, %99) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> - (%101) = "pd_op.add" (%98, %100) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> - (%102) = "pd_op.relu" (%101) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> - (%103) = "pd_op.conv2d" (%102, %35) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> - (%104) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%105) = "pd_op.reshape" (%34, %104) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%106) = "pd_op.add" (%103, %105) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%107) = "pd_op.relu" (%106) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%108) = "pd_op.conv2d" (%102, %33) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> - (%109) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%110) = "pd_op.reshape" (%32, %109) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%111) = "pd_op.add" (%108, %110) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%112) = "pd_op.relu" (%111) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%113) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_2/",value:1} : () -> tensor<1xi32> - (%114) = "builtin.combine" (%107, %112) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] - (%115) = "pd_op.concat" (%114, %113) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_2/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> - (%116) = "pd_op.conv2d" (%115, %31) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32> - (%117) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%118) = "pd_op.reshape" (%30, %117) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32> - (%119) = "pd_op.add" (%116, %118) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32> - (%120) = "pd_op.relu" (%119) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv/"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32> - (%121) = "pd_op.conv2d" (%120, %29) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32> - (%122) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%123) = "pd_op.reshape" (%28, %122) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%124) = "pd_op.add" (%121, %123) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%125) = "pd_op.relu" (%124) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_1/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%126) = "pd_op.conv2d" (%120, %27) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32> - (%127) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%128) = "pd_op.reshape" (%26, %127) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32> - (%129) = "pd_op.add" (%126, %128) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32> - (%130) = "pd_op.relu" (%129) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/MakeFireConv_2/"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32> - (%131) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_3/",value:1} : () -> tensor<1xi32> - (%132) = "builtin.combine" (%125, %130) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>] - (%133) = "pd_op.concat" (%132, %131) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_3/"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32> - (%134) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MaxPool2D_2/",value:[3,3]} : () -> tensor<2xi64> - (%135) = "pd_op.pool2d" (%133, %134) {adaptive:false,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"max",stop_gradient:[false],strides:[2,2],struct_name:"/SqueezeNet/MaxPool2D_2/"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32> - (%136) = "pd_op.conv2d" (%135, %25) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32> - (%137) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%138) = "pd_op.reshape" (%24, %137) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> - (%139) = "pd_op.add" (%136, %138) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> - (%140) = "pd_op.relu" (%139) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> - (%141) = "pd_op.conv2d" (%140, %23) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> - (%142) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%143) = "pd_op.reshape" (%22, %142) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%144) = "pd_op.add" (%141, %143) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%145) = "pd_op.relu" (%144) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%146) = "pd_op.conv2d" (%140, %21) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> - (%147) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%148) = "pd_op.reshape" (%20, %147) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%149) = "pd_op.add" (%146, %148) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%150) = "pd_op.relu" (%149) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%151) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_4/",value:1} : () -> tensor<1xi32> - (%152) = "builtin.combine" (%145, %150) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] - (%153) = "pd_op.concat" (%152, %151) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_4/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> - (%154) = "pd_op.conv2d" (%153, %19) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32> - (%155) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%156) = "pd_op.reshape" (%18, %155) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32> - (%157) = "pd_op.add" (%154, %156) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32> - (%158) = "pd_op.relu" (%157) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv/"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32> - (%159) = "pd_op.conv2d" (%158, %17) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32> - (%160) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%161) = "pd_op.reshape" (%16, %160) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%162) = "pd_op.add" (%159, %161) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%163) = "pd_op.relu" (%162) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_1/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%164) = "pd_op.conv2d" (%158, %15) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32> - (%165) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%166) = "pd_op.reshape" (%14, %165) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32> - (%167) = "pd_op.add" (%164, %166) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32> - (%168) = "pd_op.relu" (%167) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/MakeFireConv_2/"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32> - (%169) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_5/",value:1} : () -> tensor<1xi32> - (%170) = "builtin.combine" (%163, %168) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>] - (%171) = "pd_op.concat" (%170, %169) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_5/"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32> - (%172) = "pd_op.conv2d" (%171, %13) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32> - (%173) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%174) = "pd_op.reshape" (%12, %173) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%175) = "pd_op.add" (%172, %174) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> - (%176) = "pd_op.relu" (%175) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> - (%177) = "pd_op.conv2d" (%176, %11) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> - (%178) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%179) = "pd_op.reshape" (%10, %178) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%180) = "pd_op.add" (%177, %179) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%181) = "pd_op.relu" (%180) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%182) = "pd_op.conv2d" (%176, %9) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> - (%183) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%184) = "pd_op.reshape" (%8, %183) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%185) = "pd_op.add" (%182, %184) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%186) = "pd_op.relu" (%185) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%187) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_6/",value:1} : () -> tensor<1xi32> - (%188) = "builtin.combine" (%181, %186) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] - (%189) = "pd_op.concat" (%188, %187) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_6/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> - (%190) = "pd_op.conv2d" (%189, %7) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32> - (%191) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%192) = "pd_op.reshape" (%6, %191) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32> - (%193) = "pd_op.add" (%190, %192) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32> - (%194) = "pd_op.relu" (%193) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv/"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32> - (%195) = "pd_op.conv2d" (%194, %5) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32> - (%196) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%197) = "pd_op.reshape" (%4, %196) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%198) = "pd_op.add" (%195, %197) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%199) = "pd_op.relu" (%198) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_1/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%200) = "pd_op.conv2d" (%194, %3) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32> - (%201) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%202) = "pd_op.reshape" (%2, %201) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32> - (%203) = "pd_op.add" (%200, %202) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32> - (%204) = "pd_op.relu" (%203) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/MakeFireConv_2/"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32> - (%205) = "pd_op.full" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/MakeFire_7/",value:1} : () -> tensor<1xi32> - (%206) = "builtin.combine" (%199, %204) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>] - (%207) = "pd_op.concat" (%206, %205) {stop_gradient:[false],struct_name:"/SqueezeNet/MakeFire_7/"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32> - (%208) = "pd_op.full" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:"/SqueezeNet/Dropout/",value:0.5} : () -> tensor<1xf32> - (%209, %210) = "pd_op.dropout" (%207, <>, %208) {fix_seed:false,is_test:false,mode:"downgrade_in_infer",seed:0,stop_gradient:[false,false],struct_name:"/SqueezeNet/Dropout/"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8> - (%211) = "pd_op.conv2d" (%209, %1) {data_format:"NCHW",dilations:[1,1],groups:1,padding_algorithm:"EXPLICIT",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32> - (%212) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/Conv2D_1/",value:[1,-1,1,1]} : () -> tensor<4xi64> - (%213) = "pd_op.reshape" (%0, %212) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32> - (%214) = "pd_op.add" (%211, %213) {stop_gradient:[false],struct_name:"/SqueezeNet/Conv2D_1/"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32> - (%215) = "pd_op.relu" (%214) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32> - (%216) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/",value:[1,1]} : () -> tensor<2xi64> - (%217) = "pd_op.pool2d" (%215, %216) {adaptive:true,ceil_mode:false,data_format:"NCHW",exclusive:true,global_pooling:false,padding_algorithm:"EXPLICIT",paddings:[0,0],pooling_type:"avg",stop_gradient:[false],strides:[1,1],struct_name:"/SqueezeNet/AdaptiveAvgPool2D/"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32> - (%218) = "pd_op.full_int_array" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:"/SqueezeNet/",value:[2,3]} : () -> tensor<2xi64> - (%219) = "pd_op.squeeze" (%217, %218) {stop_gradient:[false],struct_name:"/SqueezeNet/"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32> -} + "protocol": "PIR", + "program_desc": "{\n (%0) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_25.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000xf32>\n (%1) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_25.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<1000x512x1x1xf32>\n (%2) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_24.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32>\n (%3) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_24.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32>\n (%4) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_23.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32>\n (%5) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_23.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32>\n (%6) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_22.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%7) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_22.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x512x1x1xf32>\n (%8) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_21.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32>\n (%9) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_21.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x3x3xf32>\n (%10) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_20.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256xf32>\n (%11) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_20.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<256x64x1x1xf32>\n (%12) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_19.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%13) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_19.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x384x1x1xf32>\n (%14) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_18.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32>\n (%15) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_18.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32>\n (%16) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_17.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32>\n (%17) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_17.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32>\n (%18) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_16.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32>\n (%19) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_16.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x384x1x1xf32>\n (%20) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_15.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32>\n (%21) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_15.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x3x3xf32>\n (%22) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_14.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192xf32>\n (%23) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_14.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<192x48x1x1xf32>\n (%24) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_13.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48xf32>\n (%25) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_13.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<48x256x1x1xf32>\n (%26) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_12.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32>\n (%27) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_12.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32>\n (%28) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_11.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32>\n (%29) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_11.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32>\n (%30) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_10.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32>\n (%31) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_10.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x256x1x1xf32>\n (%32) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_9.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32>\n (%33) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_9.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x3x3xf32>\n (%34) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_8.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128xf32>\n (%35) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_8.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<128x32x1x1xf32>\n (%36) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_7.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32xf32>\n (%37) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_7.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<32x128x1x1xf32>\n (%38) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_6.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%39) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_6.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32>\n (%40) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_5.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%41) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_5.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32>\n (%42) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_4.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32>\n (%43) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_4.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x128x1x1xf32>\n (%44) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_3.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%45) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_3.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x3x3xf32>\n (%46) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_2.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%47) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_2.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x16x1x1xf32>\n (%48) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_1.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16xf32>\n (%49) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_1.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<16x64x1x1xf32>\n (%50) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_0.b_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64xf32>\n (%51) = \"builtin.parameter\" () {is_distributed:[false],is_parameter:[true],need_clip:[true],parameter_name:\"conv2d_0.w_0\",persistable:[true],stop_gradient:[false],trainable:[true]} : () -> tensor<64x3x3x3xf32>\n (%52) = \"pd_op.data\" () {dtype:float32,name:\"image\",place:Place(undefined:0),shape:[1,3,224,224],stop_gradient:[true]} : () -> tensor<1x3x224x224xf32>\n (%53) = \"pd_op.conv2d\" (%52, %51) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[2,2],struct_name:\"/SqueezeNet/Conv2D/\"} : (tensor<1x3x224x224xf32>, tensor<64x3x3x3xf32>) -> tensor<1x64x112x112xf32>\n (%54) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%55) = \"pd_op.reshape\" (%50, %54) {stop_gradient:[false],struct_name:\"/SqueezeNet/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%56) = \"pd_op.add\" (%53, %55) {stop_gradient:[false],struct_name:\"/SqueezeNet/Conv2D/\"} : (tensor<1x64x112x112xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x112x112xf32>\n (%57) = \"pd_op.relu\" (%56) {stop_gradient:[false],struct_name:\"/SqueezeNet/\"} : (tensor<1x64x112x112xf32>) -> tensor<1x64x112x112xf32>\n (%58) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MaxPool2D/\",value:[3,3]} : () -> tensor<2xi64>\n (%59) = \"pd_op.pool2d\" (%57, %58) {adaptive:false,ceil_mode:false,data_format:\"NCHW\",exclusive:true,global_pooling:false,padding_algorithm:\"EXPLICIT\",paddings:[0,0],pooling_type:\"max\",stop_gradient:[false],strides:[2,2],struct_name:\"/SqueezeNet/MaxPool2D/\"} : (tensor<1x64x112x112xf32>, tensor<2xi64>) -> tensor<1x64x55x55xf32>\n (%60) = \"pd_op.conv2d\" (%59, %49) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/\"} : (tensor<1x64x55x55xf32>, tensor<16x64x1x1xf32>) -> tensor<1x16x55x55xf32>\n (%61) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%62) = \"pd_op.reshape\" (%48, %61) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/\"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32>\n (%63) = \"pd_op.add\" (%60, %62) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv/Conv2D/\"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32>\n (%64) = \"pd_op.relu\" (%63) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv/\"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32>\n (%65) = \"pd_op.conv2d\" (%64, %47) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/\"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32>\n (%66) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%67) = \"pd_op.reshape\" (%46, %66) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%68) = \"pd_op.add\" (%65, %67) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_1/Conv2D/\"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32>\n (%69) = \"pd_op.relu\" (%68) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_1/\"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32>\n (%70) = \"pd_op.conv2d\" (%64, %45) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/\"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32>\n (%71) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%72) = \"pd_op.reshape\" (%44, %71) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%73) = \"pd_op.add\" (%70, %72) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_2/Conv2D/\"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32>\n (%74) = \"pd_op.relu\" (%73) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/MakeFireConv_2/\"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32>\n (%75) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire/\",value:1} : () -> tensor<1xi32>\n (%76) = \"builtin.combine\" (%69, %74) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/\"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>]\n (%77) = \"pd_op.concat\" (%76, %75) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire/\"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32>\n (%78) = \"pd_op.conv2d\" (%77, %43) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/\"} : (tensor<1x128x55x55xf32>, tensor<16x128x1x1xf32>) -> tensor<1x16x55x55xf32>\n (%79) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%80) = \"pd_op.reshape\" (%42, %79) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/\"} : (tensor<16xf32>, tensor<4xi64>) -> tensor<1x16x1x1xf32>\n (%81) = \"pd_op.add\" (%78, %80) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv/Conv2D/\"} : (tensor<1x16x55x55xf32>, tensor<1x16x1x1xf32>) -> tensor<1x16x55x55xf32>\n (%82) = \"pd_op.relu\" (%81) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv/\"} : (tensor<1x16x55x55xf32>) -> tensor<1x16x55x55xf32>\n (%83) = \"pd_op.conv2d\" (%82, %41) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/\"} : (tensor<1x16x55x55xf32>, tensor<64x16x1x1xf32>) -> tensor<1x64x55x55xf32>\n (%84) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%85) = \"pd_op.reshape\" (%40, %84) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%86) = \"pd_op.add\" (%83, %85) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_1/Conv2D/\"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32>\n (%87) = \"pd_op.relu\" (%86) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_1/\"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32>\n (%88) = \"pd_op.conv2d\" (%82, %39) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/\"} : (tensor<1x16x55x55xf32>, tensor<64x16x3x3xf32>) -> tensor<1x64x55x55xf32>\n (%89) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%90) = \"pd_op.reshape\" (%38, %89) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%91) = \"pd_op.add\" (%88, %90) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_2/Conv2D/\"} : (tensor<1x64x55x55xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x55x55xf32>\n (%92) = \"pd_op.relu\" (%91) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/MakeFireConv_2/\"} : (tensor<1x64x55x55xf32>) -> tensor<1x64x55x55xf32>\n (%93) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_1/\",value:1} : () -> tensor<1xi32>\n (%94) = \"builtin.combine\" (%87, %92) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/\"} : (tensor<1x64x55x55xf32>, tensor<1x64x55x55xf32>) -> vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>]\n (%95) = \"pd_op.concat\" (%94, %93) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_1/\"} : (vec[tensor<1x64x55x55xf32>,tensor<1x64x55x55xf32>], tensor<1xi32>) -> tensor<1x128x55x55xf32>\n (%96) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MaxPool2D_1/\",value:[3,3]} : () -> tensor<2xi64>\n (%97) = \"pd_op.pool2d\" (%95, %96) {adaptive:false,ceil_mode:false,data_format:\"NCHW\",exclusive:true,global_pooling:false,padding_algorithm:\"EXPLICIT\",paddings:[0,0],pooling_type:\"max\",stop_gradient:[false],strides:[2,2],struct_name:\"/SqueezeNet/MaxPool2D_1/\"} : (tensor<1x128x55x55xf32>, tensor<2xi64>) -> tensor<1x128x27x27xf32>\n (%98) = \"pd_op.conv2d\" (%97, %37) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/\"} : (tensor<1x128x27x27xf32>, tensor<32x128x1x1xf32>) -> tensor<1x32x27x27xf32>\n (%99) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%100) = \"pd_op.reshape\" (%36, %99) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/\"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32>\n (%101) = \"pd_op.add\" (%98, %100) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv/Conv2D/\"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32>\n (%102) = \"pd_op.relu\" (%101) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv/\"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32>\n (%103) = \"pd_op.conv2d\" (%102, %35) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/\"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32>\n (%104) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%105) = \"pd_op.reshape\" (%34, %104) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/\"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32>\n (%106) = \"pd_op.add\" (%103, %105) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_1/Conv2D/\"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32>\n (%107) = \"pd_op.relu\" (%106) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_1/\"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32>\n (%108) = \"pd_op.conv2d\" (%102, %33) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/\"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32>\n (%109) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%110) = \"pd_op.reshape\" (%32, %109) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/\"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32>\n (%111) = \"pd_op.add\" (%108, %110) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_2/Conv2D/\"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32>\n (%112) = \"pd_op.relu\" (%111) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/MakeFireConv_2/\"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32>\n (%113) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_2/\",value:1} : () -> tensor<1xi32>\n (%114) = \"builtin.combine\" (%107, %112) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/\"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>]\n (%115) = \"pd_op.concat\" (%114, %113) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_2/\"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32>\n (%116) = \"pd_op.conv2d\" (%115, %31) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/\"} : (tensor<1x256x27x27xf32>, tensor<32x256x1x1xf32>) -> tensor<1x32x27x27xf32>\n (%117) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%118) = \"pd_op.reshape\" (%30, %117) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/\"} : (tensor<32xf32>, tensor<4xi64>) -> tensor<1x32x1x1xf32>\n (%119) = \"pd_op.add\" (%116, %118) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv/Conv2D/\"} : (tensor<1x32x27x27xf32>, tensor<1x32x1x1xf32>) -> tensor<1x32x27x27xf32>\n (%120) = \"pd_op.relu\" (%119) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv/\"} : (tensor<1x32x27x27xf32>) -> tensor<1x32x27x27xf32>\n (%121) = \"pd_op.conv2d\" (%120, %29) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/\"} : (tensor<1x32x27x27xf32>, tensor<128x32x1x1xf32>) -> tensor<1x128x27x27xf32>\n (%122) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%123) = \"pd_op.reshape\" (%28, %122) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/\"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32>\n (%124) = \"pd_op.add\" (%121, %123) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_1/Conv2D/\"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32>\n (%125) = \"pd_op.relu\" (%124) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_1/\"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32>\n (%126) = \"pd_op.conv2d\" (%120, %27) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/\"} : (tensor<1x32x27x27xf32>, tensor<128x32x3x3xf32>) -> tensor<1x128x27x27xf32>\n (%127) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%128) = \"pd_op.reshape\" (%26, %127) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/\"} : (tensor<128xf32>, tensor<4xi64>) -> tensor<1x128x1x1xf32>\n (%129) = \"pd_op.add\" (%126, %128) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_2/Conv2D/\"} : (tensor<1x128x27x27xf32>, tensor<1x128x1x1xf32>) -> tensor<1x128x27x27xf32>\n (%130) = \"pd_op.relu\" (%129) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/MakeFireConv_2/\"} : (tensor<1x128x27x27xf32>) -> tensor<1x128x27x27xf32>\n (%131) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_3/\",value:1} : () -> tensor<1xi32>\n (%132) = \"builtin.combine\" (%125, %130) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/\"} : (tensor<1x128x27x27xf32>, tensor<1x128x27x27xf32>) -> vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>]\n (%133) = \"pd_op.concat\" (%132, %131) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_3/\"} : (vec[tensor<1x128x27x27xf32>,tensor<1x128x27x27xf32>], tensor<1xi32>) -> tensor<1x256x27x27xf32>\n (%134) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MaxPool2D_2/\",value:[3,3]} : () -> tensor<2xi64>\n (%135) = \"pd_op.pool2d\" (%133, %134) {adaptive:false,ceil_mode:false,data_format:\"NCHW\",exclusive:true,global_pooling:false,padding_algorithm:\"EXPLICIT\",paddings:[0,0],pooling_type:\"max\",stop_gradient:[false],strides:[2,2],struct_name:\"/SqueezeNet/MaxPool2D_2/\"} : (tensor<1x256x27x27xf32>, tensor<2xi64>) -> tensor<1x256x13x13xf32>\n (%136) = \"pd_op.conv2d\" (%135, %25) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/\"} : (tensor<1x256x13x13xf32>, tensor<48x256x1x1xf32>) -> tensor<1x48x13x13xf32>\n (%137) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%138) = \"pd_op.reshape\" (%24, %137) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/\"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32>\n (%139) = \"pd_op.add\" (%136, %138) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv/Conv2D/\"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32>\n (%140) = \"pd_op.relu\" (%139) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv/\"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32>\n (%141) = \"pd_op.conv2d\" (%140, %23) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/\"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32>\n (%142) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%143) = \"pd_op.reshape\" (%22, %142) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/\"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32>\n (%144) = \"pd_op.add\" (%141, %143) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_1/Conv2D/\"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32>\n (%145) = \"pd_op.relu\" (%144) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_1/\"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32>\n (%146) = \"pd_op.conv2d\" (%140, %21) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/\"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32>\n (%147) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%148) = \"pd_op.reshape\" (%20, %147) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/\"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32>\n (%149) = \"pd_op.add\" (%146, %148) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_2/Conv2D/\"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32>\n (%150) = \"pd_op.relu\" (%149) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/MakeFireConv_2/\"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32>\n (%151) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_4/\",value:1} : () -> tensor<1xi32>\n (%152) = \"builtin.combine\" (%145, %150) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/\"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>]\n (%153) = \"pd_op.concat\" (%152, %151) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_4/\"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32>\n (%154) = \"pd_op.conv2d\" (%153, %19) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/\"} : (tensor<1x384x13x13xf32>, tensor<48x384x1x1xf32>) -> tensor<1x48x13x13xf32>\n (%155) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%156) = \"pd_op.reshape\" (%18, %155) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/\"} : (tensor<48xf32>, tensor<4xi64>) -> tensor<1x48x1x1xf32>\n (%157) = \"pd_op.add\" (%154, %156) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv/Conv2D/\"} : (tensor<1x48x13x13xf32>, tensor<1x48x1x1xf32>) -> tensor<1x48x13x13xf32>\n (%158) = \"pd_op.relu\" (%157) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv/\"} : (tensor<1x48x13x13xf32>) -> tensor<1x48x13x13xf32>\n (%159) = \"pd_op.conv2d\" (%158, %17) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/\"} : (tensor<1x48x13x13xf32>, tensor<192x48x1x1xf32>) -> tensor<1x192x13x13xf32>\n (%160) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%161) = \"pd_op.reshape\" (%16, %160) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/\"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32>\n (%162) = \"pd_op.add\" (%159, %161) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_1/Conv2D/\"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32>\n (%163) = \"pd_op.relu\" (%162) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_1/\"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32>\n (%164) = \"pd_op.conv2d\" (%158, %15) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/\"} : (tensor<1x48x13x13xf32>, tensor<192x48x3x3xf32>) -> tensor<1x192x13x13xf32>\n (%165) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%166) = \"pd_op.reshape\" (%14, %165) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/\"} : (tensor<192xf32>, tensor<4xi64>) -> tensor<1x192x1x1xf32>\n (%167) = \"pd_op.add\" (%164, %166) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_2/Conv2D/\"} : (tensor<1x192x13x13xf32>, tensor<1x192x1x1xf32>) -> tensor<1x192x13x13xf32>\n (%168) = \"pd_op.relu\" (%167) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/MakeFireConv_2/\"} : (tensor<1x192x13x13xf32>) -> tensor<1x192x13x13xf32>\n (%169) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_5/\",value:1} : () -> tensor<1xi32>\n (%170) = \"builtin.combine\" (%163, %168) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/\"} : (tensor<1x192x13x13xf32>, tensor<1x192x13x13xf32>) -> vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>]\n (%171) = \"pd_op.concat\" (%170, %169) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_5/\"} : (vec[tensor<1x192x13x13xf32>,tensor<1x192x13x13xf32>], tensor<1xi32>) -> tensor<1x384x13x13xf32>\n (%172) = \"pd_op.conv2d\" (%171, %13) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/\"} : (tensor<1x384x13x13xf32>, tensor<64x384x1x1xf32>) -> tensor<1x64x13x13xf32>\n (%173) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%174) = \"pd_op.reshape\" (%12, %173) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%175) = \"pd_op.add\" (%172, %174) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv/Conv2D/\"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32>\n (%176) = \"pd_op.relu\" (%175) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv/\"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32>\n (%177) = \"pd_op.conv2d\" (%176, %11) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/\"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32>\n (%178) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%179) = \"pd_op.reshape\" (%10, %178) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/\"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32>\n (%180) = \"pd_op.add\" (%177, %179) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_1/Conv2D/\"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32>\n (%181) = \"pd_op.relu\" (%180) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_1/\"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32>\n (%182) = \"pd_op.conv2d\" (%176, %9) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/\"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32>\n (%183) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%184) = \"pd_op.reshape\" (%8, %183) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/\"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32>\n (%185) = \"pd_op.add\" (%182, %184) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_2/Conv2D/\"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32>\n (%186) = \"pd_op.relu\" (%185) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/MakeFireConv_2/\"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32>\n (%187) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_6/\",value:1} : () -> tensor<1xi32>\n (%188) = \"builtin.combine\" (%181, %186) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/\"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>]\n (%189) = \"pd_op.concat\" (%188, %187) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_6/\"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32>\n (%190) = \"pd_op.conv2d\" (%189, %7) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/\"} : (tensor<1x512x13x13xf32>, tensor<64x512x1x1xf32>) -> tensor<1x64x13x13xf32>\n (%191) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%192) = \"pd_op.reshape\" (%6, %191) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/\"} : (tensor<64xf32>, tensor<4xi64>) -> tensor<1x64x1x1xf32>\n (%193) = \"pd_op.add\" (%190, %192) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv/Conv2D/\"} : (tensor<1x64x13x13xf32>, tensor<1x64x1x1xf32>) -> tensor<1x64x13x13xf32>\n (%194) = \"pd_op.relu\" (%193) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv/\"} : (tensor<1x64x13x13xf32>) -> tensor<1x64x13x13xf32>\n (%195) = \"pd_op.conv2d\" (%194, %5) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/\"} : (tensor<1x64x13x13xf32>, tensor<256x64x1x1xf32>) -> tensor<1x256x13x13xf32>\n (%196) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%197) = \"pd_op.reshape\" (%4, %196) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/\"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32>\n (%198) = \"pd_op.add\" (%195, %197) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_1/Conv2D/\"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32>\n (%199) = \"pd_op.relu\" (%198) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_1/\"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32>\n (%200) = \"pd_op.conv2d\" (%194, %3) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[1,1],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/\"} : (tensor<1x64x13x13xf32>, tensor<256x64x3x3xf32>) -> tensor<1x256x13x13xf32>\n (%201) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%202) = \"pd_op.reshape\" (%2, %201) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/\"} : (tensor<256xf32>, tensor<4xi64>) -> tensor<1x256x1x1xf32>\n (%203) = \"pd_op.add\" (%200, %202) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_2/Conv2D/\"} : (tensor<1x256x13x13xf32>, tensor<1x256x1x1xf32>) -> tensor<1x256x13x13xf32>\n (%204) = \"pd_op.relu\" (%203) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/MakeFireConv_2/\"} : (tensor<1x256x13x13xf32>) -> tensor<1x256x13x13xf32>\n (%205) = \"pd_op.full\" () {dtype:int32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/MakeFire_7/\",value:1} : () -> tensor<1xi32>\n (%206) = \"builtin.combine\" (%199, %204) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/\"} : (tensor<1x256x13x13xf32>, tensor<1x256x13x13xf32>) -> vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>]\n (%207) = \"pd_op.concat\" (%206, %205) {stop_gradient:[false],struct_name:\"/SqueezeNet/MakeFire_7/\"} : (vec[tensor<1x256x13x13xf32>,tensor<1x256x13x13xf32>], tensor<1xi32>) -> tensor<1x512x13x13xf32>\n (%208) = \"pd_op.full\" () {dtype:float32,place:Place(cpu),shape:[1],stop_gradient:[true],struct_name:\"/SqueezeNet/Dropout/\",value:0.5} : () -> tensor<1xf32>\n (%209, %210) = \"pd_op.dropout\" (%207, <>, %208) {fix_seed:false,is_test:false,mode:\"downgrade_in_infer\",seed:0,stop_gradient:[false,false],struct_name:\"/SqueezeNet/Dropout/\"} : (tensor<1x512x13x13xf32>, <>, tensor<1xf32>) -> tensor<1x512x13x13xf32>, tensor<1x512x13x13xu8>\n (%211) = \"pd_op.conv2d\" (%209, %1) {data_format:\"NCHW\",dilations:[1,1],groups:1,padding_algorithm:\"EXPLICIT\",paddings:[0,0],stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/Conv2D_1/\"} : (tensor<1x512x13x13xf32>, tensor<1000x512x1x1xf32>) -> tensor<1x1000x13x13xf32>\n (%212) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/Conv2D_1/\",value:[1,-1,1,1]} : () -> tensor<4xi64>\n (%213) = \"pd_op.reshape\" (%0, %212) {stop_gradient:[false],struct_name:\"/SqueezeNet/Conv2D_1/\"} : (tensor<1000xf32>, tensor<4xi64>) -> tensor<1x1000x1x1xf32>\n (%214) = \"pd_op.add\" (%211, %213) {stop_gradient:[false],struct_name:\"/SqueezeNet/Conv2D_1/\"} : (tensor<1x1000x13x13xf32>, tensor<1x1000x1x1xf32>) -> tensor<1x1000x13x13xf32>\n (%215) = \"pd_op.relu\" (%214) {stop_gradient:[false],struct_name:\"/SqueezeNet/\"} : (tensor<1x1000x13x13xf32>) -> tensor<1x1000x13x13xf32>\n (%216) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/AdaptiveAvgPool2D/\",value:[1,1]} : () -> tensor<2xi64>\n (%217) = \"pd_op.pool2d\" (%215, %216) {adaptive:true,ceil_mode:false,data_format:\"NCHW\",exclusive:true,global_pooling:false,padding_algorithm:\"EXPLICIT\",paddings:[0,0],pooling_type:\"avg\",stop_gradient:[false],strides:[1,1],struct_name:\"/SqueezeNet/AdaptiveAvgPool2D/\"} : (tensor<1x1000x13x13xf32>, tensor<2xi64>) -> tensor<1x1000x1x1xf32>\n (%218) = \"pd_op.full_int_array\" () {dtype:int64,place:Place(cpu),stop_gradient:[true],struct_name:\"/SqueezeNet/\",value:[2,3]} : () -> tensor<2xi64>\n (%219) = \"pd_op.squeeze\" (%217, %218) {stop_gradient:[false],struct_name:\"/SqueezeNet/\"} : (tensor<1x1000x1x1xf32>, tensor<2xi64>) -> tensor<1x1000xf32>\n}\n" +} \ No newline at end of file