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.

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

Tensor pad transform limitations doc #3295

Merged
merged 1 commit into from
Jan 26, 2021
Merged

Tensor pad transform limitations doc #3295

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 5 additions & 2 deletions torchvision/transforms/functional.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -384,7 +384,9 @@ def scale(*args, **kwargs):
def pad(img: Tensor, padding: List[int], fill: int = 0, padding_mode: str = "constant") -> Tensor:
r"""Pad the given image on all sides with the given "pad" value.
If the image is torch Tensor, it is expected
to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
to have [..., H, W] shape, where ... means at most 2 leading dimensions for mode reflect and symmetric,
at most 3 leading dimensions for mode edge,
and an arbitrary number of leading dimensions for mode constant

Args:
img (PIL Image or Tensor): Image to be padded.
Expand All @@ -402,7 +404,8 @@ def pad(img: Tensor, padding: List[int], fill: int = 0, padding_mode: str = "con

- constant: pads with a constant value, this value is specified with fill

- edge: pads with the last value on the edge of the image
- edge: pads with the last value on the edge of the image,
if input a 5D torch Tensor, the last 3 dimensions will be padded instead of the last 2

- reflect: pads with reflection of image (without repeating the last value on the edge)

Expand Down
10 changes: 7 additions & 3 deletions torchvision/transforms/transforms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -319,7 +319,9 @@ def __repr__(self):
class Pad(torch.nn.Module):
"""Pad the given image on all sides with the given "pad" value.
If the image is torch Tensor, it is expected
to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
to have [..., H, W] shape, where ... means at most 2 leading dimensions for mode reflect and symmetric,
at most 3 leading dimensions for mode edge,
and an arbitrary number of leading dimensions for mode constant

Args:
padding (int or sequence): Padding on each border. If a single int is provided this
Expand All @@ -337,7 +339,8 @@ class Pad(torch.nn.Module):

- constant: pads with a constant value, this value is specified with fill

- edge: pads with the last value at the edge of the image
- edge: pads with the last value at the edge of the image,
if input a 5D torch Tensor, the last 3 dimensions will be padded instead of the last 2

- reflect: pads with reflection of image without repeating the last value on the edge

Expand Down Expand Up @@ -491,7 +494,8 @@ def __call__(self, img):
class RandomCrop(torch.nn.Module):
"""Crop the given image at a random location.
If the image is torch Tensor, it is expected
to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions,
but if non-constant padding is used, the input is expected to have at most 2 leading dimensions

Args:
size (sequence or int): Desired output size of the crop. If size is an
Expand Down