[BUG] - MarioRL Resize Bug

[alperenunlu]

Add Link

mario_rl_tutorial.py

Describe the bug

On MarioRL Tutorial resize function gives warning in newer versions.

python intermediate_source/mario_rl_tutorial.py

UserWarning: The default value of the antialias parameter of all the resizing transforms > (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to > be consistent across the PIL and Tensor backends. To suppress this warning, directly pass > antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).

Describe your environment

Platform: macOS
CUDA: no
PyTorch version: 2.1.0

cc @vmoens @nairbv @sekyondaMeta @svekars @carljparker @NicolasHug @kit1980 @subramen

[alperenunlu]

@svekars

[alperenunlu]

/assigntome

[github-actions]

This issue does not have the correct label. Please pick an opened and unnasigned issue with the docathon-h2-2023 label.

[svekars]

@vmoens any thoughts?

[vmoens]

As the warning says, the use of Resize should have the flag antialias=True. That should not impact the performance of the learning algorithm