Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix CutMix and MixUp arguments in transforms.py #8287

Merged
merged 2 commits into from
Mar 4, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion references/classification/train.py
Original file line number Diff line number Diff line change
Expand Up @@ -222,7 +222,7 @@ def main(args):

num_classes = len(dataset.classes)
mixup_cutmix = get_mixup_cutmix(
mixup_alpha=args.mixup_alpha, cutmix_alpha=args.cutmix_alpha, num_categories=num_classes, use_v2=args.use_v2
mixup_alpha=args.mixup_alpha, cutmix_alpha=args.cutmix_alpha, num_classes=num_classes, use_v2=args.use_v2
)
if mixup_cutmix is not None:

Expand Down
10 changes: 5 additions & 5 deletions references/classification/transforms.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,21 +7,21 @@
from torchvision.transforms import functional as F


def get_mixup_cutmix(*, mixup_alpha, cutmix_alpha, num_categories, use_v2):
def get_mixup_cutmix(*, mixup_alpha, cutmix_alpha, num_classes, use_v2):

Check warning on line 10 in references/classification/transforms.py

View workflow job for this annotation

GitHub Actions / bc

Function get_mixup_cutmix: num_categories was removed

Check warning on line 10 in references/classification/transforms.py

View workflow job for this annotation

GitHub Actions / bc

Function get_mixup_cutmix: num_classes was added and is now required
transforms_module = get_module(use_v2)

mixup_cutmix = []
if mixup_alpha > 0:
mixup_cutmix.append(
transforms_module.MixUp(alpha=mixup_alpha, num_categories=num_categories)
transforms_module.MixUp(alpha=mixup_alpha, num_classes=num_classes)
if use_v2
else RandomMixUp(num_classes=num_categories, p=1.0, alpha=mixup_alpha)
else RandomMixUp(num_classes=num_classes, p=1.0, alpha=mixup_alpha)
)
if cutmix_alpha > 0:
mixup_cutmix.append(
transforms_module.CutMix(alpha=mixup_alpha, num_categories=num_categories)
transforms_module.CutMix(alpha=mixup_alpha, num_classes=num_classes)
if use_v2
else RandomCutMix(num_classes=num_categories, p=1.0, alpha=mixup_alpha)
else RandomCutMix(num_classes=num_classes, p=1.0, alpha=mixup_alpha)
)
if not mixup_cutmix:
return None
Expand Down
Loading