Error Code 4: Internal Error (Network must have at least one output)

[alicera]

https://github.com/linghu8812/tensorrt_inference/tree/master/project/yolov7#2export-onnx-model

model

work/AI/YOLOv7/tensorrt/tensorrt_inference/project/build# ../../bin/tensorrt_inference yolov7 ../../configs/yolov7/config.yaml ../../samples/detection_segmentation/bus.jpg 
read file error: ../configs/labels/coco.names
[10/28/2022-13:28:08] [I] [TRT] [MemUsageChange] Init CUDA: CPU +196, GPU +0, now: CPU 203, GPU 8098 (MiB)
[10/28/2022-13:28:09] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +6, GPU +2, now: CPU 228, GPU 8100 (MiB)
[10/28/2022-13:28:09] [I] [TRT] ----------------------------------------------------------------
[10/28/2022-13:28:09] [I] [TRT] Input filename:   ../weights/yolov7.onnx
[10/28/2022-13:28:09] [I] [TRT] ONNX IR version:  0.0.6
[10/28/2022-13:28:09] [I] [TRT] Opset version:    12
[10/28/2022-13:28:09] [I] [TRT] Producer name:    pytorch
[10/28/2022-13:28:09] [I] [TRT] Producer version: 1.10
[10/28/2022-13:28:09] [I] [TRT] Domain:           
[10/28/2022-13:28:09] [I] [TRT] Model version:    0
[10/28/2022-13:28:09] [I] [TRT] Doc string:       
[10/28/2022-13:28:09] [I] [TRT] ----------------------------------------------------------------
[10/28/2022-13:28:09] [W] [TRT] parsers/onnx/onnx2trt_utils.cpp:367: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[10/28/2022-13:28:09] [E] [TRT] [graphShapeAnalyzer.cpp::analyzeShapes::1294] Error Code 4: Miscellaneous (IElementWiseLayer Mul_322: broadcast dimensions must be conformable)
[10/28/2022-13:28:09] [E] [TRT] parsers/onnx/ModelImporter.cpp:773: While parsing node number 322 [Mul -> "528"]:
[10/28/2022-13:28:09] [E] [TRT] parsers/onnx/ModelImporter.cpp:774: --- Begin node ---
[10/28/2022-13:28:09] [E] [TRT] parsers/onnx/ModelImporter.cpp:775: input: "525"
input: "657"
output: "528"
name: "Mul_322"
op_type: "Mul"

[10/28/2022-13:28:09] [E] [TRT] parsers/onnx/ModelImporter.cpp:776: --- End node ---
[10/28/2022-13:28:09] [E] [TRT] parsers/onnx/ModelImporter.cpp:778: ERROR: parsers/onnx/ModelImporter.cpp:180 In function parseGraph:
[6] Invalid Node - Mul_322
[graphShapeAnalyzer.cpp::analyzeShapes::1294] Error Code 4: Miscellaneous (IElementWiseLayer Mul_322: broadcast dimensions must be conformable)
[10/28/2022-13:28:09] [E] Failure while parsing ONNX file
start building engine
[10/28/2022-13:28:09] [E] [TRT] 4: [network.cpp::validate::2671] Error Code 4: Internal Error (Network must have at least one output)
build engine done
tensorrt_inference: /work/AI/YOLOv7/tensorrt/tensorrt_inference/code/src/model.cpp:46: void Model::OnnxToTRTModel(): Assertion `engine' failed.
Aborted (core dumped)

[nuriakiin]

I have same issue. did you solve it?

[linghu8812]

I have same issue. did you solve it?

@nuriakiin try to download ONNX models from here:
https://pan.baidu.com/s/1Ff_SA9Q66DUnZjSipPa74Q, code: opkp

[nuriakiin]

@linghu8812 thank you. i solve it with original repo. I was trying with your Export.py on forked repo.