search

alexandrosstergiou / SoftPool

[ICCV 2021] Code for approximated exponential maximum pooling
MIT License
288 stars 52 forks source link

pytorch inplace operation issue #47

Closed git-luo66 closed 2 years ago

git-luo66 commented 2 years ago

hello This is my mistake! RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 256, 40, 40]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

The error ends here！ grad_input = torch.zeros_like(ctx.saved_tensors[0]) May I ask what caused the problem thank you！

alexandrosstergiou commented 2 years ago

Hi @git-luo66 ,

Judging from the line of code you have highlighted, you are using the CUDA implementation of the code and not the inplace version. Assuming this, the error relates to an operation that happens after SoftPool. I would suggest to check that you are not using Relu with inplace=True. Another easy solution is to create a deep copy of the input before/after applying SoftPool.