Vadim Kantorov

Strangely enough, installing opencv+pytorch from conda and then installing torchvision from pip seems to work: ```shell conda install -y opencv pytorch cudatoolkit=11.1 -c pytorch -c conda-forge python -m pip install...

I'll then rename this issue to propose dropping torchvision 0.2.2 from conda algotether (I think error is more preferred than so outdated installation)

Another instance is at https://github.com/pytorch/vision/issues/5374 I think it would help a lot of debugging time to simply remove version 0.2.2 from all package managers, it is massively outdated and hides...

IMO that antique 0.2.2 package should just be deleted from conda-forge regardless of other general better maintentership practices...

I have no affiliation with torchvision / FAIR etc so I'm not speaking for pytorch/torchvision maintainers or the team :) So my messages are no more than just an opinion,...

At the point of creating this issue, the example in OP was repro (and in issues there were other cases like this, but I don't have them at hand). But...

cc @atalman

This would also introduce inconsistency with core PyTorch F.pad, F.conv2d padding argument (which has string values of same/valid)

yes, and the question stays the same: is introducing more inconsistencies the way forward? is pytorch core going to adopt enums? what're core teams thoughts on this? why does core...

well, `resize_size` makes think that it's resizing the input instead and always gives a fixed output resolution from what I understand, the two impl I mentioned above allow for scaling...