Jeffrey Zimmerman

icon location Physicist & computer scientist currently working on machine learning applications at Summit Wash Holdings

Results 3 comments of Jeffrey Zimmerman

Mslogin and login on register

This passes/fails all the same tests that the main branch does.

Transforms v2.RandomRotation fail when expand=True with ValueError(f"Found multiple HxW dimensions in the sample: {sequence_to_str(sorted(sizes))}")

Same thing happened with WIDERFace dataset. It seems inherent to the image/box rotation. When `expand=True`, image rotation uses `_get_inverse_affine_matrix([0, 0], angle, translate, scale, shear)` while box rotation uses `_get_inverse_affine_matrix(center, angle,...

Transforms v2.RandomRotation fail when expand=True with ValueError(f"Found multiple HxW dimensions in the sample: {sequence_to_str(sorted(sizes))}")

I see the problem now. The sizes are still affected, but without a call to `torchvision.transforms.v2._utils.query_size()`, they not checked for mismatch. In addition, WIDERFace does not have a `transforms` argument,...