Non contiguous arrays?

[giuliolovisotto]

Hi, I found a problem reproducing the basic example in https://github.com/microsoft/robust-models-transfer (I downloaded resnet18_l2_eps3.ckpt).

Problem is that I get NaN values for accuracy. If I print the exception caught at Line 470 of robustness/train.py it says the following UserWarning: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

I investigated a bit and I can fix this by adding .contiguous() in the accuracy computation in robustness/tools/helpers.py:
correct_k = correct[:k].contiguous().view(-1).float(), I found a similar issue here cezannec/capsule_net_pytorch#4. The problem was when computing top-5 accuracy specifically (I assume it would happen with everything higher than top-1). Changing that line made everything work again.

I haven't opened a pull request because I'm not sure why this happens in my setup, I am running everything inside this docker container and on an Nvidia Titan RTX.

[andrewilyas]

Thanks for making an issue! Does this still happen with the latest version of the library? We became aware of this issue (it actually only happens with PyTorch 1.7) a few months ago and so we changed that line to use .reshape() instead:

robustness/robustness/tools/helpers.py

Line 75 in 79d371f

correct_k = correct[:k].reshape(-1).float()

The updated version should be available on PyPI; let us know if the problem persists after a pip install --upgrade robustness!

[giuliolovisotto]

Great thanks, updating to the newest version fixed it! Don't know if you want to change the robustness version in the requirements.txt file for the other project.