Skip to content

fix MixUp and CutMix #6464

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.

Sign up for GitHub

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

Merged
merged 3 commits into from
Aug 23, 2022
Merged

fix MixUp and CutMix #6464

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d93c759
fix MixUp and CutMix
pmeier Aug 22, 2022
096c3b0
improve error message
pmeier Aug 23, 2022
eb0b90f
Merge branch 'main' into cutmix-mixup-pil
pmeier Aug 23, 2022
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
22 changes: 14 additions & 8 deletions torchvision/prototype/transforms/_augment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,10 +99,8 @@ def __init__(self, *, alpha: float, p: float = 0.5) -> None:

def forward(self, *inpts: Any) -> Any:
sample = inpts if len(inpts) > 1 else inpts[0]
if not (
has_any(sample, features.Image, PIL.Image.Image, is_simple_tensor) and has_any(sample, features.OneHotLabel)
):
raise TypeError(f"{type(self).__name__}() is only defined for Image's *and* OneHotLabel's.")
if not (has_any(sample, features.Image, is_simple_tensor) and has_any(sample, features.OneHotLabel)):
raise TypeError(f"{type(self).__name__}() is only defined for tensor images and one-hot labels.")
if has_any(sample, features.BoundingBox, features.SegmentationMask, features.Label):
raise TypeError(
f"{type(self).__name__}() does not support bounding boxes, segmentation masks and plain labels."
Expand All @@ -123,12 +121,16 @@ def _get_params(self, sample: Any) -> Dict[str, Any]:

def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
lam = params["lam"]
if isinstance(inpt, features.Image):
if isinstance(inpt, features.Image) or is_simple_tensor(inpt):
if inpt.ndim < 4:
raise ValueError("Need a batch of images")
output = inpt.clone()
output = output.roll(1, -4).mul_(1 - lam).add_(output.mul_(lam))
return features.Image.new_like(inpt, output)

if isinstance(inpt, features.Image):
output = features.Image.new_like(inpt, output)

return output
elif isinstance(inpt, features.OneHotLabel):
return self._mixup_onehotlabel(inpt, lam)
else:
Expand Down Expand Up @@ -159,15 +161,19 @@ def _get_params(self, sample: Any) -> Dict[str, Any]:
return dict(box=box, lam_adjusted=lam_adjusted)

def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
if isinstance(inpt, features.Image):
if isinstance(inpt, features.Image) or is_simple_tensor(inpt):
box = params["box"]
if inpt.ndim < 4:
raise ValueError("Need a batch of images")
x1, y1, x2, y2 = box
image_rolled = inpt.roll(1, -4)
output = inpt.clone()
output[..., y1:y2, x1:x2] = image_rolled[..., y1:y2, x1:x2]
return features.Image.new_like(inpt, output)

if isinstance(inpt, features.Image):
output = features.Image.new_like(inpt, output)

return output
elif isinstance(inpt, features.OneHotLabel):
lam_adjusted = params["lam_adjusted"]
return self._mixup_onehotlabel(inpt, lam_adjusted)
Expand Down