pytorch2onnx.py TypeError: forward() got multiple values for argument 'return_loss'

[pekopoke]

my env list:
mmcls 0.25.0
mmcv-full 1.7.1
mmdet 2.28.2

branch : master

python /opt/mmclassification/tools/deployment/pytorch2onnx.py /opt/mmclassification/configs/resnet/resnet18_8xb16_cifar10.py --checkpoint ./resnet18_b16x8_cifar10_20210528-bd6371c8.pth --output-file resnet18_b16x8_cifar10_20210528-bd6371c8.onnx --dynamic-export --show --simplify --verify

Traceback (most recent call last):
  File "/opt/mmclassification/tools/deployment/pytorch2onnx.py", line 220, in <module>
    verify=args.verify)
  File "/opt/mmclassification/tools/deployment/pytorch2onnx.py", line 107, in pytorch2onnx
    opset_version=opset_version)
  File "/opt/conda/lib/python3.7/site-packages/torch/onnx/__init__.py", line 365, in export
    export_modules_as_functions,
  File "/opt/conda/lib/python3.7/site-packages/torch/onnx/utils.py", line 178, in export
    export_modules_as_functions=export_modules_as_functions,
  File "/opt/conda/lib/python3.7/site-packages/torch/onnx/utils.py", line 1084, in _export
    dynamic_axes=dynamic_axes,
  File "/opt/conda/lib/python3.7/site-packages/torch/onnx/utils.py", line 727, in _model_to_graph
    graph, params, torch_out, module = _create_jit_graph(model, args)
  File "/opt/conda/lib/python3.7/site-packages/torch/onnx/utils.py", line 602, in _create_jit_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/opt/conda/lib/python3.7/site-packages/torch/onnx/utils.py", line 518, in _trace_and_get_graph_from_model
    model, args, strict=False, _force_outplace=False, _return_inputs_states=True
  File "/opt/conda/lib/python3.7/site-packages/torch/jit/_trace.py", line 1175, in _get_trace_graph
    outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/torch/jit/_trace.py", line 132, in forward
    self._force_outplace,
  File "/opt/conda/lib/python3.7/site-packages/torch/jit/_trace.py", line 118, in wrapper
    outs.append(self.inner(*trace_inputs))
  File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1118, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/opt/mmcv/mmcv/runner/fp16_utils.py", line 119, in new_func
    return old_func(*args, **kwargs)
TypeError: forward() got multiple values for argument 'return_loss'

[Songhuilun]

Hello, is your problem solved?

[Songhuilun]

can you help me?