Vasilis Vryniotis

@frgfm Just wanted to check in and ensure you are not blocked or need any assistance. Let me know if you do. :)

@frgfm Ah yes the unit-tests. I would recommend following the pattern that we have on existing tests and have a similar coverage. Hopefully following the existing infra will make your...

@giangdip2410 I can't reproduce the problem. The following works fine with me: ``` import torchvision torchvision.models.get_model('vit_h_14', weights='DEFAULT') ``` Judging from your error message: ``` RuntimeError: PytorchStreamReader failed reading zip archive:...

@oke-aditya Thanks for the proposal. Here are some thoughts: Concerning Large, we would have to reproduce the training of the model. We didn't do it because it would take time...

For a very long time, we allowed models without weights. In the last release @YosuaMichael trained the last remaining variants. Models with no weights used to create issues to various...

> PIL uses anti-aliasing by default and this is what our models where trained on, but we don't pass antialias=True to the [Resize transform](https://github.com/pytorch/vision/blob/5737ed27c7937c6bbb6774be90d61bc6e68f6d06/torchvision/transforms/_presets.py#L56), so it might be a source...

@NicolasHug thanks for publishing the results this looks very interesting. It's obvious that antialiasing will have a massive effect to users when they start using more the Tensor backend. @pmeier...

# PIL Backend I'm doing the following runs to confirm the validity on PIL backend. ## Classification ### Augmentation: ta_wide + random erasing + mixup + cutmix Target Acc: 80.854...

# PIL Backend Due to the bug discovered at #6541, we need to repeat the experiments that involve the LSJ. ### Augmentation: lsj + copypaste Target Acc: 0.473 / 0.417...

@pmeier @vfdev-5 I think we just confirmed that the v2 produces the same model accuracy as v1. GGs! :) I don't think we can easily make arguments about speed because...