ResNet50训练模型(flowers102数据集)-paddle-onnx-ir-engine

<?xml version="1.0" ?> <net name="paddle-onnx" version="11"> <layers> <layer id="0" name="x" type="Parameter" version="opset1"> <data shape="1,3,224,224" element_type="f32"/> <rt_info> <attribute name="fused_names" version="0" value="x"/> </rt_info> <output> <port id="0" precision="FP32" names="x"> <dim>1</dim> <dim>3</dim> <dim>224</dim> <dim>224</dim> </port> </output> </layer> <layer id="1" name="Multiply_8831" type="Const" version="opset1"> <data element_type="f32" shape="32, 3, 3, 3" offset="0" size="3456"/> <output> <port id="0" precision="FP32"> <dim>32</dim> <dim>3</dim> <dim>3</dim> <dim>3</dim> </port> </output> </layer> <layer id="2" name="Multiply_8439" type="Convolution" version="opset1"> <data strides="2, 2" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit"/> <rt_info> <attribute name="fused_names" version="0" value="batch_norm_0.b_0, batch_norm_0.tmp_3, batch_norm_0.w_0, batch_norm_0.w_1, batch_norm_0.w_2, conv2d_55.tmp_0"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>3</dim> <dim>224</dim> <dim>224</dim> </port> <port id="1" precision="FP32"> <dim>32</dim> <dim>3</dim> <dim>3</dim> <dim>3</dim> </port> </input> <output> <port id="2" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="3" name="Constant_8444" type="Const" version="opset1"> <data element_type="f32" shape="1, 32, 1, 1" offset="3456" size="128"/> <output> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>1</dim> <dim>1</dim> </port> </output> </layer> <layer id="4" name="batch_norm_0.tmp_3" type="Add" version="opset1"> <data auto_broadcast="numpy"/> <rt_info> <attribute name="fused_names" version="0" value="batch_norm_0.b_0, batch_norm_0.tmp_3, batch_norm_0.w_0, batch_norm_0.w_1, batch_norm_0.w_2"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> <port id="1" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>1</dim> <dim>1</dim> </port> </input> <output> <port id="2" precision="FP32" names="batch_norm_0.tmp_3"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="5" name="relu_0.tmp_0" type="ReLU" version="opset1"> <rt_info> <attribute name="fused_names" version="0" value="relu_0.tmp_0"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </input> <output> <port id="1" precision="FP32" names="relu_0.tmp_0"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="6" name="Multiply_8840" type="Const" version="opset1"> <data element_type="f32" shape="32, 32, 3, 3" offset="3584" size="36864"/> <output> <port id="0" precision="FP32"> <dim>32</dim> <dim>32</dim> <dim>3</dim> <dim>3</dim> </port> </output> </layer> <layer id="7" name="Multiply_8446" type="Convolution" version="opset1"> <data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit"/> <rt_info> <attribute name="fused_names" version="0" value="batch_norm_1.b_0, batch_norm_1.tmp_3, batch_norm_1.w_0, batch_norm_1.w_1, batch_norm_1.w_2, conv2d_56.tmp_0"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> <port id="1" precision="FP32"> <dim>32</dim> <dim>32</dim> <dim>3</dim> <dim>3</dim> </port> </input> <output> <port id="2" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="8" name="Constant_8451" type="Const" version="opset1"> <data element_type="f32" shape="1, 32, 1, 1" offset="40448" size="128"/> <output> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>1</dim> <dim>1</dim> </port> </output> </layer> <layer id="9" name="batch_norm_1.tmp_3" type="Add" version="opset1"> <data auto_broadcast="numpy"/> <rt_info> <attribute name="fused_names" version="0" value="batch_norm_1.b_0, batch_norm_1.tmp_3, batch_norm_1.w_0, batch_norm_1.w_1, batch_norm_1.w_2"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> <port id="1" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>1</dim> <dim>1</dim> </port> </input> <output> <port id="2" precision="FP32" names="batch_norm_1.tmp_3"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="10" name="relu_1.tmp_0" type="ReLU" version="opset1"> <rt_info> <attribute name="fused_names" version="0" value="relu_1.tmp_0"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </input> <output> <port id="1" precision="FP32" names="relu_1.tmp_0"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="11" name="Multiply_8849" type="Const" version="opset1"> <data element_type="f32" shape="64, 32, 3, 3" offset="40576" size="73728"/> <output> <port id="0" precision="FP32"> <dim>64</dim> <dim>32</dim> <dim>3</dim> <dim>3</dim> </port> </output> </layer> <layer id="12" name="Multiply_8453" type="Convolution" version="opset1"> <data strides="1, 1" dilations="1, 1" pads_begin="1, 1" pads_end="1, 1" auto_pad="explicit"/> <rt_info> <attribute name="fused_names" version="0" value="batch_norm_2.b_0, batch_norm_2.tmp_3, batch_norm_2.w_0, batch_norm_2.w_1, batch_norm_2.w_2, conv2d_57.tmp_0"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>32</dim> <dim>112</dim> <dim>112</dim> </port> <port id="1" precision="FP32"> <dim>64</dim> <dim>32</dim> <dim>3</dim> <dim>3</dim> </port> </input> <output> <port id="2" precision="FP32"> <dim>1</dim> <dim>64</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="13" name="Constant_8458" type="Const" version="opset1"> <data element_type="f32" shape="1, 64, 1, 1" offset="114304" size="256"/> <output> <port id="0" precision="FP32"> <dim>1</dim> <dim>64</dim> <dim>1</dim> <dim>1</dim> </port> </output> </layer> <layer id="14" name="batch_norm_2.tmp_3" type="Add" version="opset1"> <data auto_broadcast="numpy"/> <rt_info> <attribute name="fused_names" version="0" value="batch_norm_2.b_0, batch_norm_2.tmp_3, batch_norm_2.w_0, batch_norm_2.w_1, batch_norm_2.w_2"/> </rt_info> <input> <port id="0" precision="FP32"> <dim>1</dim> <dim>64</dim> <dim>112</dim> <dim>112</dim> </port> <port id="1" precision="FP32"> <dim>1</dim> <dim>64</dim> <dim>1</dim> <dim>1</dim> </port> </input> <output> <port id="2" precision="FP32" names="batch_norm_2.tmp_3"> <dim>1</dim> <dim>64</dim> <dim>112</dim> <dim>112</dim> </port> </output> </layer> <layer id="15" name="relu_2.tmp_0" type="ReLU" version="opset1"> <rt_info> <attribute name="fused_names" version="0" value="relu_2.tmp_0"/> </rt_info> <input> <port id="0" precision="FP32">