You did a great job, but I found a bug when I went to run example_pspnet.py
Traceback (most recent call last):
File "D:\Aipre\RepVGG-main\example_pspnet.py", line 141, in
y_train = model(input)
File "E:\anaconda3\envs\hooke_3.9\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, *kwargs)
File "D:\Aipre\RepVGG-main\example_pspnet.py", line 107, in forward
x = self.layer1(x)
File "E:\anaconda3\envs\hooke_3.9\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(input, **kwargs)
File "E:\anaconda3\envs\hooke_3.9\lib\site-packages\torch\nn\modules\module.py", line 201, in _forward_unimplemented
raise NotImplementedError
NotImplementedError
I found the wrong reason:
The return value of the_make_stage method in the repvgg.py file is return nn.ModuleList(blocks)
Change it to return nn.Sequential(*blocks)
You did a great job, but I found a bug when I went to run example_pspnet.py
Traceback (most recent call last): File "D:\Aipre\RepVGG-main\example_pspnet.py", line 141, in
y_train = model(input)
File "E:\anaconda3\envs\hooke_3.9\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, *kwargs)
File "D:\Aipre\RepVGG-main\example_pspnet.py", line 107, in forward
x = self.layer1(x)
File "E:\anaconda3\envs\hooke_3.9\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(input, **kwargs)
File "E:\anaconda3\envs\hooke_3.9\lib\site-packages\torch\nn\modules\module.py", line 201, in _forward_unimplemented
raise NotImplementedError
NotImplementedError