Run failed.

[livermoressss]

I convert the model to onnx and run the helper.
python3 torch2onnx.py /arcface_torch/wf42m_pfc03_40epoch_64gpu_vit_l/model.pt --output arcface_torch_wf42m_pfc03_40epoch_64gpu_vit_l.onnx --network vit_l_dp005_mask_005

After I run python3 onnx_helper.py ./ I got this error. @nttstar

Traceback (most recent call last):
  File "/opt/tiger/insightface/recognition/arcface_torch/onnx_helper.py", line 249, in <module>
    err = handler.check(args.track)
  File "/opt/tiger/insightface/recognition/arcface_torch/onnx_helper.py", line 164, in check
    batch_result = self.check_batch(test_img)
  File "/opt/tiger/insightface/recognition/arcface_torch/onnx_helper.py", line 198, in check_batch
    net_out = self.session.run(self.output_names, {self.input_name: blob})[0]
  File "/home/tiger/.local/lib/python3.9/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'/blocks.0/attn/Reshape' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:45 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{32,144,2304}, requested shape:{1,144,3,8,96}