Invalid Node - Mul_446

[gzw820]

[07/10/2022-18:30:00] [E] [TRT] ModelImporter.cpp:774: --- Begin node --- [07/10/2022-18:30:00] [E] [TRT] ModelImporter.cpp:775: input: "642" input: "1341" output: "645" name: "Mul_446" op_type: "Mul"

[07/10/2022-18:30:00] [E] [TRT] ModelImporter.cpp:776: --- End node --- [07/10/2022-18:30:00] [E] [TRT] ModelImporter.cpp:779: ERROR: ModelImporter.cpp:180 In function parseGraph: [6] Invalid Node - Mul_446 [graphShapeAnalyzer.cpp::analyzeShapes::1294] Error Code 4: Miscellaneous (IElementWiseLayer Mul_446: broadcast dimensions must be conformable) [07/10/2022-18:30:00] [E] Failed to parse onnx file [07/10/2022-18:30:00] [I] Finish parsing network model [07/10/2022-18:30:00] [E] Parsing model failed [07/10/2022-18:30:00] [E] Failed to create engine from model or file. [07/10/2022-18:30:00] [E] Engine set up failed &&&& FAILED TensorRT.trtexec [TensorRT v8401] # ./trtexec --onnx=./yolov7.onnx --saveEngine=./yolov7_fp16.engine --fp16 --workspace=200

[gzw820]

[07/10/2022-18:42:46] [E] [TRT] ModelImporter.cpp:775: input: "646" input: "1345" output: "649" name: "Mul_450" op_type: "Mul"

[07/10/2022-18:42:46] [E] [TRT] ModelImporter.cpp:776: --- End node --- [07/10/2022-18:42:46] [E] [TRT] ModelImporter.cpp:779: ERROR: ModelImporter.cpp:180 In function parseGraph: [6] Invalid Node - Mul_450 [graphShapeAnalyzer.cpp::analyzeShapes::1294] Error Code 4: Miscellaneous (IElementWiseLayer Mul_450: broadcast dimensions must be conformable) [07/10/2022-18:42:46] [E] Failed to parse onnx file [07/10/2022-18:42:46] [I] Finish parsing network model [07/10/2022-18:42:46] [E] Parsing model failed [07/10/2022-18:42:46] [E] Failed to create engine from model or file. [07/10/2022-18:42:46] [E] Engine set up failed &&&& FAILED TensorRT.trtexec [TensorRT v8401] # ./trtexec --onnx=./yolov7.onnx --saveEngine=./yolov7_fp16.engine --fp16 --workspace=200

[Monday-Leo]

降低pytroch版本至1.7.1再导出ONNX模型。torch1.10-cu102会出这个问题。