Nicolas Hug

Hi @crazyboy9103 , thanks for the report. I'm not so familiar with that part of the code-base so I could be way off, but I suspect the logic you're looking...

Thanks for the report @nps1ngh . Good catch! For all torchivsion models, the correct reference for accuracies should be this table: https://pytorch.org/vision/main/models.html#table-of-all-available-classification-weights (or the [specific model pages like the one...

Hi @davidgill97 , sorry, I don't think I'll be able to prioritize ONNX-related issues from now.

Hi @qlzh727 , I don't recommend that you keep relying on the torchvision video decoder - we're deprecating it in favor of torchcodec: https://github.com/pytorch/torchcodec

Thanks for the PR @mrdbourke , can you please look into fixing this test: ``` ___________________________ test_draw_boxes_warning ____________________________ test/test_utils.py:211: in test_draw_boxes_warning with pytest.warns(UserWarning, match=re.escape("Argument 'font_size' will be ignored since 'font'...

Sorry @V0XNIHILI , if we were to sort the input we'd be running the risk of outputting the dataset in a different order than how it was originally packaged. Ensuring...

I think storing a copy of the original order would have to be part of the original dataset, but that's not somethin torchvision can control, only the dataset authors can...

Hi folks, thanks for the feature request. We have basic support for C++ extensions as described in https://github.com/pytorch/vision/tree/main/examples/cpp, but note that this isn't actively maintained / developed. It's not thoroughly...

Thanks for the PR @SeanScripts . Have you found that useful in practice? Note that we aren't adding more features to the traditional `torchvision.transforms` namespace. New features and enhancements should...

Thanks for the RP @MalumaDev . Can you share more details - why is this something you need?