Skip to content

GitLab

Unverified Commit 972ca657 authored by Loi Ly's avatar Loi Ly Committed by GitHub
Browse files

Update docstring for RandAugment (#4457) 

* update docstring for RandAugment

* update docstrings for pillow image
parent c6a03c76
Hide whitespace changes
Inline Side-by-side
Showing with 6 additions and 6 deletions
torchvision/transforms/autoaugment.py
View file @ 972ca657
...@@ -65,8 +65,8 @@ class AutoAugment(torch.nn.Module): ...@@ -65,8 +65,8 @@ class AutoAugment(torch.nn.Module):
r"""AutoAugment data augmentation method based on r"""AutoAugment data augmentation method based on
`"AutoAugment: Learning Augmentation Strategies from Data" <https://arxiv.org/pdf/1805.09501.pdf>`_. `"AutoAugment: Learning Augmentation Strategies from Data" <https://arxiv.org/pdf/1805.09501.pdf>`_.
If the image is torch Tensor, it should be of type torch.uint8, and it is expected If the image is torch Tensor, it should be of type torch.uint8, and it is expected
to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. to have [..., 3, H, W] shape, where ... means an arbitrary number of leading dimensions.
If img is PIL Image, it is expected to be in mode "L" or "RGB". If img is PIL Image, it is expected to be in mode "RGB".
Args: Args:
policy (AutoAugmentPolicy): Desired policy enum defined by policy (AutoAugmentPolicy): Desired policy enum defined by
...@@ -249,8 +249,8 @@ class RandAugment(torch.nn.Module): ...@@ -249,8 +249,8 @@ class RandAugment(torch.nn.Module):
`"RandAugment: Practical automated data augmentation with a reduced search space" `"RandAugment: Practical automated data augmentation with a reduced search space"
<https://arxiv.org/abs/1909.13719>`_. <https://arxiv.org/abs/1909.13719>`_.
If the image is torch Tensor, it should be of type torch.uint8, and it is expected If the image is torch Tensor, it should be of type torch.uint8, and it is expected
to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. to have [..., 3, H, W] shape, where ... means an arbitrary number of leading dimensions.
If img is PIL Image, it is expected to be in mode "L" or "RGB". If img is PIL Image, it is expected to be in mode "RGB".
Args: Args:
num_ops (int): Number of augmentation transformations to apply sequentially. num_ops (int): Number of augmentation transformations to apply sequentially.
...@@ -333,8 +333,8 @@ class TrivialAugmentWide(torch.nn.Module): ...@@ -333,8 +333,8 @@ class TrivialAugmentWide(torch.nn.Module):
r"""Dataset-independent data-augmentation with TrivialAugment Wide, as described in r"""Dataset-independent data-augmentation with TrivialAugment Wide, as described in
`"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation" <https://arxiv.org/abs/2103.10158>`. `"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation" <https://arxiv.org/abs/2103.10158>`.
If the image is torch Tensor, it should be of type torch.uint8, and it is expected If the image is torch Tensor, it should be of type torch.uint8, and it is expected
to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. to have [..., 3, H, W] shape, where ... means an arbitrary number of leading dimensions.
If img is PIL Image, it is expected to be in mode "L" or "RGB". If img is PIL Image, it is expected to be in mode "RGB".
Args: Args:
num_magnitude_bins (int): The number of different magnitude values. num_magnitude_bins (int): The number of different magnitude values.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment