Nicolas Hug

Thanks for the feedback @ctr26 . I'm still not sure I completely understand why `FakeData` and `VisionDataset` need to have the same signature. But since this seems to be a...

``` [pip3] torchvision==0.16.2+cu121 [conda] torchvision 0.16.2+cu121 pypi_0 pypi ``` Try uninstalling these versions first?

> Built Torch 2.1.2 and TorchVision 2.1.2 from source What version of torchvision are you building from source, exactly? There's no torchvision 2.x. The latest stable version is 0.17. The...

What build script are you referring to? Can you share the build command you used?

Hi @JillCakmak . Are you referring to this line? ```py model = torch.hub.load('pytorch/vision:v0.10.0', 'densenet121', pretrained=True) ``` This one works fine for me

Thanks for the PR @aljkor Can you share more details on what this is fixing exactly?

Thanks for the report @Xact-sniper . This will be fixed by https://github.com/pytorch/vision/pull/8426. What you're trying to do won't work on the V2 version, I'm not sure why just yet, I've...

Looks like the first part of this issue, i.e. introducing nearest-exact mode, was addressed in https://github.com/pytorch/vision/pull/6754. The other part is to decide whether we want to change the default of...

Thanks for the PR @Floyd2yh . The `ImageFolder` class exposes a `loader` attribute that you can override to a custom loader. I'd suggest simply doing that locally. Unfortunately we won't...

yeah, the current template addresses these points it seems: > It should describe the existing problem that it is trying to solve and why this SLEP makes the situation better....