search

NVlabs / pacnet

Pixel-Adaptive Convolutional Neural Networks (CVPR '19)
https://suhangpro.github.io/pac/
Other
514 stars 79 forks source link

Got an error when using PacConv2d #7

Open Qi-X opened 5 years ago

Qi-X commented 5 years ago

I want to use PacConv2d, but I got an error when I ran the code. It seems that it was an inplace operation problem, and I don't know why.

Traceback (most recent call last): File "main.py", line 167, in train() File "main.py", line 147, in train loss.backward() File "/usr/local/lib/python2.7/dist-packages/torch/tensor.py", line 93, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/usr/local/lib/python2.7/dist-packages/torch/autograd/init.py", line 89, in backward allow_unreachable=True) # allow_unreachable flag File "/usr/local/lib/python2.7/dist-packages/torch/autograd/function.py", line 76, in apply return self._forward_cls.backward(self, args) File "/usr/local/lib/python2.7/dist-packages/torch/autograd/function.py", line 188, in wrapper outputs = fn(ctx, args) File "/home/xq/contrast_convlstm/pac.py", line 182, in backward input, kernel, weight = ctx.saved_tensors RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

The error located at class PacConv2dFn(Function) backward function. I hope your advice. Thanks.

suhangpro commented 5 years ago

I am not sure whether that matters but we only tested with Python3. Can you please report your Pytorch version? Also, do all the tests pass?

Qi-X commented 5 years ago

I use python2, pytorch0.4.0. I don't know how to do all the tests.

suhangpro commented 5 years ago

python -m unittest will run all tests. Seeing whether any fails and which ones can help us diagnose.