self.cache[n] = getattr(self, n)(*[self.cache[x] for x in i])，run it python3.5,it make a mistake.

[Clarence-wen]

File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(input, **kwargs)
File "/home/clarence/cifar10-fast/torch_backend.py", line 126, in forward
self.cache[n] = getattr(self, n)([self.cache[x] for x in i])
File "/home/clarence/cifar10-fast/torch_backend.py", line 126, in
self.cache[n] = getattr(self, n)(*[self.cache[x] for x in i])
KeyError: 'classifier'

[lioujheyu]

I had the same issue and found this is caused by the implementation change of dict between python 3.5 and 3.6.

What I did to solve this problem is to replace all dict and {} with OrderedDict in python 3.5.