转出onnx模型，在优化阶段报错。

[runner-9]

[11/29 19:37:01 fastreid.onnx_export]: Beginning ONNX file converting
/home/dourenyin/anaconda3/envs/fastreid/lib/python3.7/site-packages/torch/onnx/utils.py:243: UserWarning: add_node_names' can be set to True only when 'operator_export_type' is ONNX. Since 'operator_export_type' is not set to 'ONNX', add_node_names argument will be ignored. "{}argument will be ignored.".format(arg_name, arg_name)) /home/dourenyin/anaconda3/envs/fastreid/lib/python3.7/site-packages/torch/onnx/utils.py:243: UserWarning:do_constant_folding' can be set to True only when 'operator_export_type' is ONNX. Since 'operator_export_type' is not set to 'ONNX', do_constant_folding argument will be ignored.
"{} argument will be ignored.".format(arg_name, arg_name))
[11/29 19:37:03 fastreid.onnx_export]: Completed convert of ONNX model
[11/29 19:37:03 fastreid.onnx_export]: Beginning ONNX model path optimization
[11/29 19:37:04 fastreid.onnx_export]: Completed ONNX model path optimization
Traceback (most recent call last):
File "tools/deploy/onnx_export.py", line 158, in
model_simp, check = simplify(onnx_model)
File "/home/dourenyin/anaconda3/envs/fastreid/lib/python3.7/site-packages/onnxsim/onnx_simplifier.py", line 204, in simplify
tensor_size_threshold,
onnx.onnx_cpp2py_export.shape_inference.InferenceError: [ShapeInferenceError] Inferred shape and existing shape differ in rank: (1) vs (4)