ONNX Inference failed. Non-zero status code returned while running Reshape node.

[inSight-mk1]

Export yolov5l-xs-1.pt to ONNX format using export.py in this repo,
Then do the detect, ONNX model was loaded successfully, but it failed when running this code
pred = torch.tensor(self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: img}))
It threw:
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'Reshape_222' Status Message: D:\a\_work\1\s\onnxruntime\core/providers/cpu/tensor/reshape_helper.h:42 onnxruntime::ReshapeHelper::ReshapeHelper gsl::narrow_cast<int64_t>(input_shape.Size()) == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{756,1,512}, requested shape:{756,12096,32}

The same code runs yolov5's onnx model successfully.

Any plan to add onnx convert support for yolov5-TPH? Thanks you!

[inSight-mk1]

It also failed when converting to pb format. It threw:
TensorFlow saved_model: export failure: name 'C3TR' is not defined

[cv516Buaa]

Sorry, we have not used onnx to export the weight of yolov5, I will list it as one of the future work.