Not work for EfficientNet

Question

Not work for EfficientNet

lfangyu09 opened this issue 4 years ago · comments

lfangyu09 commented 4 years ago

mathmax12 · Answer 1 · Wed Jan 20 2021 13:48:59 GMT+0800 (China Standard Time)

I am looking for the same estimation for efficientNet. Did you make it work?

lfangyu09 · Answer 2 · Sun Apr 25 2021 10:55:13 GMT+0800 (China Standard Time)

Unfortunately, no

Perry Gibson · Answer 3 · Wed Mar 23 2022 01:06:48 GMT+0800 (China Standard Time)

I have also had this experience, with EfficentNet-B4. My error looks like this:

  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/segmentation_models_pytorch/encoders/efficientnet.py", line 66, in forward
    x = stages[i](x)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/container.py", line 139, in forward
    input = module(input)
  File "/usr/local/lib/python3.6/dist-packages/torchstat/model_hook.py", line 44, in wrap_call
    assert module.__class__ in self._origin_call
AssertionError