wandering007 / efficient-densenet-pytorch Goto Github PK

hi, I used the pytorch 0.3 version from https://github.com/gpleiss/efficient_densenet_pytorch. It seems the 0.3 version cost far less memory than your 0.4 version. Do you have tried to compare this?

Hi,
I have traied this model and train it based on this training code.

I tried the model using densenet40 with grouth_rate = 12 on that but only got 6.0% error rate(5.24% inthe report) when using the non-efficiency implementation and 6.1% with efficiency implementation
By the way, the memmory efficiency implementation works pretty good!
Could you please help with that?

Before testing the efficient densenet implementation, out = F.dropout(out, p=0.5, training=self.training) at Line 184 in densenet.py should be commented.

Then if I set multigpus = True in test_densenet.py, running python test_densenet.py will get the following error:

Traceback (most recent call last):
  File "test_densenet.py", line 47, in <module>
    out_effi.sum().backward()
  File "/home/changmao/miniconda3/lib/python3.5/site-packages/torch/tensor.py", line 93, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "/home/changmao/miniconda3/lib/python3.5/site-packages/torch/autograd/__init__.py", line 89, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

And I cannot locate the improper inplace operation. All I know is that the error seems occur after the error-backpropagation of few efficient bottleneck modules. All the code is run by Pytorch v0.4.0.