• D
    dhuib

    @金天 在jetson nano上用yolov3的onnx转trt报错,不知道是不是Onnx格式不一样。一定要用Onnx-tensorrt写吗,不太明白这之间的关系。

    Loading ONNX file from path yolov4_coco_m2_asff_544.onnx...
    Beginning ONNX file parsing
    Completed parsing of ONNX file
    Building an engine from file yolov4_coco_m2_asff_544.onnx; this may take a while...
    [TensorRT] ERROR: Network must have at least one output
    Completed creating Engine
    Traceback (most recent call last):
      File "onnx_to_tensorrt.py", line 185, in <module>
        main()
      File "onnx_to_tensorrt.py", line 153, in main
        with get_engine(onnx_file_path, engine_file_path) as engine, engine.create_execution_context() as context:
      File "onnx_to_tensorrt.py", line 126, in get_engine
        return build_engine()
      File "onnx_to_tensorrt.py", line 117, in build_engine
        f.write(engine.serialize())
    AttributeError: 'NoneType' object has no attribute 'serialize'
    

    发布在 原创分享专区 阅读更多

与 ManaAI社区 的连接断开,我们正在尝试重连,请耐心等待