Remove BETA status for v2 transforms (#8111)

docs/source/beta_status.py

@@ -12,18 +12,8 @@ class BetaStatus(Directive):
         return [self.node("", nodes.paragraph("", "", nodes.Text(text)))]
 
 
-class V2BetaStatus(BetaStatus):
-    text = (
-        "The {api_name} is in Beta stage, and while we do not expect disruptive breaking changes, "
-        "some APIs may slightly change according to user feedback. Please submit any feedback you may have "
-        "in this issue: https://github.com/pytorch/vision/issues/6753."
-    )
-    node = nodes.note
-
-
 def setup(app):
     app.add_directive("betastatus", BetaStatus)
-    app.add_directive("v2betastatus", V2BetaStatus)
     return {
         "version": "0.1",
         "parallel_read_safe": True,

docs/source/transforms.rst

@@ -126,13 +126,6 @@ you're already using tranforms from ``torchvision.transforms``, all you need to
 do to is to update the import to ``torchvision.transforms.v2``. In terms of
 output, there might be negligible differences due to implementation differences.
 
-.. note::
-
-    The v2 transforms are still BETA, but at this point we do not expect
-    disruptive changes to be made to their public APIs. We're planning to make
-    them fully stable in version 0.17. Please submit any feedback you may have
-    `here <https://github.com/pytorch/vision/issues/6753>`_.
-
 .. _transforms_perf:
 
 Performance considerations

torchvision/transforms/v2/_augment.py

@@ -15,9 +15,7 @@ from ._utils import _parse_labels_getter, has_any, is_pure_tensor, query_chw, qu
 
 
 class RandomErasing(_RandomApplyTransform):
-    """[BETA] Randomly select a rectangle region in the input image or video and erase its pixels.
-
-    .. v2betastatus:: RandomErasing transform
+    """Randomly select a rectangle region in the input image or video and erase its pixels.
 
     This transform does not support PIL Image.
     'Random Erasing Data Augmentation' by Zhong et al. See https://arxiv.org/abs/1708.04896
@@ -207,9 +205,7 @@ class _BaseMixUpCutMix(Transform):
 
 
 class MixUp(_BaseMixUpCutMix):
-    """[BETA] Apply MixUp to the provided batch of images and labels.
-
-    .. v2betastatus:: MixUp transform
+    """Apply MixUp to the provided batch of images and labels.
 
     Paper: `mixup: Beyond Empirical Risk Minimization <https://arxiv.org/abs/1710.09412>`_.
 
@@ -256,9 +252,7 @@ class MixUp(_BaseMixUpCutMix):
 
 
 class CutMix(_BaseMixUpCutMix):
-    """[BETA] Apply CutMix to the provided batch of images and labels.
-
-    .. v2betastatus:: CutMix transform
+    """Apply CutMix to the provided batch of images and labels.
 
     Paper: `CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
     <https://arxiv.org/abs/1905.04899>`_.

torchvision/transforms/v2/_auto_augment.py

@@ -174,11 +174,9 @@ class _AutoAugmentBase(Transform):
 
 
 class AutoAugment(_AutoAugmentBase):
-    r"""[BETA] 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>`_.
 
-    .. v2betastatus:: AutoAugment transform
-
     This transformation works on images and videos only.
 
     If the input is :class:`torch.Tensor`, it should be of type ``torch.uint8``, and it is expected
@@ -350,12 +348,10 @@ class AutoAugment(_AutoAugmentBase):
 
 
 class RandAugment(_AutoAugmentBase):
-    r"""[BETA] RandAugment data augmentation method based on
+    r"""RandAugment data augmentation method based on
     `"RandAugment: Practical automated data augmentation with a reduced search space"
     <https://arxiv.org/abs/1909.13719>`_.
 
-    .. v2betastatus:: RandAugment transform
-
     This transformation works on images and videos only.
 
     If the input is :class:`torch.Tensor`, it should be of type ``torch.uint8``, and it is expected
@@ -434,11 +430,9 @@ class RandAugment(_AutoAugmentBase):
 
 
 class TrivialAugmentWide(_AutoAugmentBase):
-    r"""[BETA] 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>`_.
 
-    .. v2betastatus:: TrivialAugmentWide transform
-
     This transformation works on images and videos only.
 
     If the input is :class:`torch.Tensor`, it should be of type ``torch.uint8``, and it is expected
@@ -505,11 +499,9 @@ class TrivialAugmentWide(_AutoAugmentBase):
 
 
 class AugMix(_AutoAugmentBase):
-    r"""[BETA] AugMix data augmentation method based on
+    r"""AugMix data augmentation method based on
     `"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty" <https://arxiv.org/abs/1912.02781>`_.
 
-    .. v2betastatus:: AugMix transform
-
     This transformation works on images and videos only.
 
     If the input is :class:`torch.Tensor`, it should be of type ``torch.uint8``, and it is expected

torchvision/transforms/v2/_color.py

@@ -10,9 +10,7 @@ from ._utils import query_chw
 
 
 class Grayscale(Transform):
-    """[BETA] Convert images or videos to grayscale.
-
-    .. v2betastatus:: Grayscale transform
+    """Convert images or videos to grayscale.
 
     If the input is a :class:`torch.Tensor`, it is expected
     to have [..., 3 or 1, H, W] shape, where ... means an arbitrary number of leading dimensions
@@ -32,9 +30,7 @@ class Grayscale(Transform):
 
 
 class RandomGrayscale(_RandomApplyTransform):
-    """[BETA] Randomly convert image or videos to grayscale with a probability of p (default 0.1).
-
-    .. v2betastatus:: RandomGrayscale transform
+    """Randomly convert image or videos to grayscale with a probability of p (default 0.1).
 
     If the input is a :class:`torch.Tensor`, it is expected to have [..., 3 or 1, H, W] shape,
     where ... means an arbitrary number of leading dimensions
@@ -59,9 +55,7 @@ class RandomGrayscale(_RandomApplyTransform):
 
 
 class ColorJitter(Transform):
-    """[BETA] Randomly change the brightness, contrast, saturation and hue of an image or video.
-
-    .. v2betastatus:: ColorJitter transform
+    """Randomly change the brightness, contrast, saturation and hue of an image or video.
 
     If the input is a :class:`torch.Tensor`, it is expected
     to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions.
@@ -163,10 +157,7 @@ class ColorJitter(Transform):
 
 
 class RandomChannelPermutation(Transform):
-    """[BETA] Randomly permute the channels of an image or video
-
-    .. v2betastatus:: RandomChannelPermutation transform
-    """
+    """Randomly permute the channels of an image or video"""
 
     def _get_params(self, flat_inputs: List[Any]) -> Dict[str, Any]:
         num_channels, *_ = query_chw(flat_inputs)
@@ -177,11 +168,9 @@ class RandomChannelPermutation(Transform):
 
 
 class RandomPhotometricDistort(Transform):
-    """[BETA] Randomly distorts the image or video as used in `SSD: Single Shot
+    """Randomly distorts the image or video as used in `SSD: Single Shot
     MultiBox Detector <https://arxiv.org/abs/1512.02325>`_.
 
-    .. v2betastatus:: RandomPhotometricDistort transform
-
     This transform relies on :class:`~torchvision.transforms.v2.ColorJitter`
     under the hood to adjust the contrast, saturation, hue, brightness, and also
     randomly permutes channels.
@@ -249,9 +238,7 @@ class RandomPhotometricDistort(Transform):
 
 
 class RandomEqualize(_RandomApplyTransform):
-    """[BETA] Equalize the histogram of the given image or video with a given probability.
-
-    .. v2betastatus:: RandomEqualize transform
+    """Equalize the histogram of the given image or video with a given probability.
 
     If the input is a :class:`torch.Tensor`, it is expected
     to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions.
@@ -268,9 +255,7 @@ class RandomEqualize(_RandomApplyTransform):
 
 
 class RandomInvert(_RandomApplyTransform):
-    """[BETA] Inverts the colors of the given image or video with a given probability.
-
-    .. v2betastatus:: RandomInvert transform
+    """Inverts the colors of the given image or video with a given probability.
 
     If img is a Tensor, it is expected to be in [..., 1 or 3, H, W] format,
     where ... means it can have an arbitrary number of leading dimensions.
@@ -287,11 +272,9 @@ class RandomInvert(_RandomApplyTransform):
 
 
 class RandomPosterize(_RandomApplyTransform):
-    """[BETA] Posterize the image or video with a given probability by reducing the
+    """Posterize the image or video with a given probability by reducing the
     number of bits for each color channel.
 
-    .. v2betastatus:: RandomPosterize transform
-
     If the input is a :class:`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.
     If img is PIL Image, it is expected to be in mode "L" or "RGB".
@@ -312,11 +295,9 @@ class RandomPosterize(_RandomApplyTransform):
 
 
 class RandomSolarize(_RandomApplyTransform):
-    """[BETA] Solarize the image or video with a given probability by inverting all pixel
+    """Solarize the image or video with a given probability by inverting all pixel
     values above a threshold.
 
-    .. v2betastatus:: RandomSolarize transform
-
     If img is a Tensor, it is expected to be in [..., 1 or 3, H, W] format,
     where ... means it can have an arbitrary number of leading dimensions.
     If img is PIL Image, it is expected to be in mode "L" or "RGB".
@@ -342,9 +323,7 @@ class RandomSolarize(_RandomApplyTransform):
 
 
 class RandomAutocontrast(_RandomApplyTransform):
-    """[BETA] Autocontrast the pixels of the given image or video with a given probability.
-
-    .. v2betastatus:: RandomAutocontrast transform
+    """Autocontrast the pixels of the given image or video with a given probability.
 
     If the input is a :class:`torch.Tensor`, it is expected
     to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions.
@@ -361,9 +340,7 @@ class RandomAutocontrast(_RandomApplyTransform):
 
 
 class RandomAdjustSharpness(_RandomApplyTransform):
-    """[BETA] Adjust the sharpness of the image or video with a given probability.
-
-    .. v2betastatus:: RandomAdjustSharpness transform
+    """Adjust the sharpness of the image or video with a given probability.
 
     If the input is a :class:`torch.Tensor`,
     it is expected to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions.

torchvision/transforms/v2/_container.py

@@ -8,9 +8,7 @@ from torchvision.transforms.v2 import Transform
 
 
 class Compose(Transform):
-    """[BETA] Composes several transforms together.
-
-    .. v2betastatus:: Compose transform
+    """Composes several transforms together.
 
     This transform does not support torchscript.
     Please, see the note below.
@@ -62,9 +60,7 @@ class Compose(Transform):
 
 
 class RandomApply(Transform):
-    """[BETA] Apply randomly a list of transformations with a given probability.
-
-    .. v2betastatus:: RandomApply transform
+    """Apply randomly a list of transformations with a given probability.
 
     .. note::
         In order to script the transformation, please use ``torch.nn.ModuleList`` as input instead of list/tuple of
@@ -118,9 +114,7 @@ class RandomApply(Transform):
 
 
 class RandomChoice(Transform):
-    """[BETA] Apply single transformation randomly picked from a list.
-
-    .. v2betastatus:: RandomChoice transform
+    """Apply single transformation randomly picked from a list.
 
     This transform does not support torchscript.
 
@@ -157,9 +151,7 @@ class RandomChoice(Transform):
 
 
 class RandomOrder(Transform):
-    """[BETA] Apply a list of transformations in a random order.
-
-    .. v2betastatus:: RandomOrder transform
+    """Apply a list of transformations in a random order.
 
     This transform does not support torchscript.
 

torchvision/transforms/v2/_deprecated.py

@@ -10,12 +10,10 @@ from torchvision.transforms.v2 import Transform
 
 
 class ToTensor(Transform):
-    """[BETA] [DEPRECATED] Use ``v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])`` instead.
+    """[DEPRECATED] Use ``v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])`` instead.
 
     Convert a PIL Image or ndarray to tensor and scale the values accordingly.
 
-    .. v2betastatus:: ToTensor transform
-
     .. warning::
         :class:`v2.ToTensor` is deprecated and will be removed in a future release.
         Please use instead ``v2.Compose([v2.ToImage(), v2.ToDtype(torch.float32, scale=True)])``.

torchvision/transforms/v2/_geometry.py

@@ -31,9 +31,7 @@ from ._utils import (
 
 
 class RandomHorizontalFlip(_RandomApplyTransform):
-    """[BETA] Horizontally flip the input with a given probability.
-
-    .. v2betastatus:: RandomHorizontalFlip transform
+    """Horizontally flip the input with a given probability.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -51,9 +49,7 @@ class RandomHorizontalFlip(_RandomApplyTransform):
 
 
 class RandomVerticalFlip(_RandomApplyTransform):
-    """[BETA] Vertically flip the input with a given probability.
-
-    .. v2betastatus:: RandomVerticalFlip transform
+    """Vertically flip the input with a given probability.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -71,9 +67,7 @@ class RandomVerticalFlip(_RandomApplyTransform):
 
 
 class Resize(Transform):
-    """[BETA] Resize the input to the given size.
-
-    .. v2betastatus:: Resize transform
+    """Resize the input to the given size.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -159,9 +153,7 @@ class Resize(Transform):
 
 
 class CenterCrop(Transform):
-    """[BETA] Crop the input at the center.
-
-    .. v2betastatus:: CenterCrop transform
+    """Crop the input at the center.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -187,9 +179,7 @@ class CenterCrop(Transform):
 
 
 class RandomResizedCrop(Transform):
-    """[BETA] Crop a random portion of the input and resize it to a given size.
-
-    .. v2betastatus:: RandomResizedCrop transform
+    """Crop a random portion of the input and resize it to a given size.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -310,9 +300,7 @@ class RandomResizedCrop(Transform):
 
 
 class FiveCrop(Transform):
-    """[BETA] Crop the image or video into four corners and the central crop.
-
-    .. v2betastatus:: FiveCrop transform
+    """Crop the image or video into four corners and the central crop.
 
     If the input is a :class:`torch.Tensor` or a :class:`~torchvision.tv_tensors.Image` or a
     :class:`~torchvision.tv_tensors.Video` it can have arbitrary number of leading batch dimensions.
@@ -371,11 +359,9 @@ class FiveCrop(Transform):
 
 
 class TenCrop(Transform):
-    """[BETA] Crop the image or video into four corners and the central crop plus the flipped version of
+    """Crop the image or video into four corners and the central crop plus the flipped version of
     these (horizontal flipping is used by default).
 
-    .. v2betastatus:: TenCrop transform
-
     If the input is a :class:`torch.Tensor` or a :class:`~torchvision.tv_tensors.Image` or a
     :class:`~torchvision.tv_tensors.Video` it can have arbitrary number of leading batch dimensions.
     For example, the image can have ``[..., C, H, W]`` shape.
@@ -418,9 +404,7 @@ class TenCrop(Transform):
 
 
 class Pad(Transform):
-    """[BETA] Pad the input on all sides with the given "pad" value.
-
-    .. v2betastatus:: Pad transform
+    """Pad the input on all sides with the given "pad" value.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -492,11 +476,9 @@ class Pad(Transform):
 
 
 class RandomZoomOut(_RandomApplyTransform):
-    """[BETA] "Zoom out" transformation from
+    """ "Zoom out" transformation from
     `"SSD: Single Shot MultiBox Detector" <https://arxiv.org/abs/1512.02325>`_.
 
-    .. v2betastatus:: RandomZoomOut transform
-
     This transformation randomly pads images, videos, bounding boxes and masks creating a zoom out effect.
     Output spatial size is randomly sampled from original size up to a maximum size configured
     with ``side_range`` parameter:
@@ -562,9 +544,7 @@ class RandomZoomOut(_RandomApplyTransform):
 
 
 class RandomRotation(Transform):
-    """[BETA] Rotate the input by angle.
-
-    .. v2betastatus:: RandomRotation transform
+    """Rotate the input by angle.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -643,9 +623,7 @@ class RandomRotation(Transform):
 
 
 class RandomAffine(Transform):
-    """[BETA] Random affine transformation the input keeping center invariant.
-
-    .. v2betastatus:: RandomAffine transform
+    """Random affine transformation the input keeping center invariant.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -765,9 +743,7 @@ class RandomAffine(Transform):
 
 
 class RandomCrop(Transform):
-    """[BETA] Crop the input at a random location.
-
-    .. v2betastatus:: RandomCrop transform
+    """Crop the input at a random location.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -922,9 +898,7 @@ class RandomCrop(Transform):
 
 
 class RandomPerspective(_RandomApplyTransform):
-    """[BETA] Perform a random perspective transformation of the input with a given probability.
-
-    .. v2betastatus:: RandomPerspective transform
+    """Perform a random perspective transformation of the input with a given probability.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -1009,9 +983,7 @@ class RandomPerspective(_RandomApplyTransform):
 
 
 class ElasticTransform(Transform):
-    """[BETA] Transform the input with elastic transformations.
-
-    .. v2betastatus:: RandomPerspective transform
+    """Transform the input with elastic transformations.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -1101,11 +1073,9 @@ class ElasticTransform(Transform):
 
 
 class RandomIoUCrop(Transform):
-    """[BETA] Random IoU crop transformation from
+    """Random IoU crop transformation from
     `"SSD: Single Shot MultiBox Detector" <https://arxiv.org/abs/1512.02325>`_.
 
-    .. v2betastatus:: RandomIoUCrop transform
-
     This transformation requires an image or video data and ``tv_tensors.BoundingBoxes`` in the input.
 
     .. warning::
@@ -1229,11 +1199,9 @@ class RandomIoUCrop(Transform):
 
 
 class ScaleJitter(Transform):
-    """[BETA] Perform Large Scale Jitter on the input according to
+    """Perform Large Scale Jitter on the input according to
     `"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation" <https://arxiv.org/abs/2012.07177>`_.
 
-    .. v2betastatus:: ScaleJitter transform
-
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
     it can have arbitrary number of leading batch dimensions. For example,
@@ -1298,9 +1266,7 @@ class ScaleJitter(Transform):
 
 
 class RandomShortestSize(Transform):
-    """[BETA] Randomly resize the input.
-
-    .. v2betastatus:: RandomShortestSize transform
+    """Randomly resize the input.
 
     If the input is a :class:`torch.Tensor` or a ``TVTensor`` (e.g. :class:`~torchvision.tv_tensors.Image`,
     :class:`~torchvision.tv_tensors.Video`, :class:`~torchvision.tv_tensors.BoundingBoxes` etc.)
@@ -1368,9 +1334,7 @@ class RandomShortestSize(Transform):
 
 
 class RandomResize(Transform):
-    """[BETA] Randomly resize the input.
-
-    .. v2betastatus:: RandomResize transform
+    """Randomly resize the input.
 
     This transformation can be used together with ``RandomCrop`` as data augmentations to train
     models on image segmentation task.

torchvision/transforms/v2/_meta.py

@@ -5,9 +5,7 @@ from torchvision.transforms.v2 import functional as F, Transform
 
 
 class ConvertBoundingBoxFormat(Transform):
-    """[BETA] Convert bounding box coordinates to the given ``format``, eg from "CXCYWH" to "XYXY".
-
-    .. v2betastatus:: ConvertBoundingBoxFormat transform
+    """Convert bounding box coordinates to the given ``format``, eg from "CXCYWH" to "XYXY".
 
     Args:
         format (str or tv_tensors.BoundingBoxFormat): output bounding box format.
@@ -28,12 +26,10 @@ class ConvertBoundingBoxFormat(Transform):
 
 
 class ClampBoundingBoxes(Transform):
-    """[BETA] Clamp bounding boxes to their corresponding image dimensions.
+    """Clamp bounding boxes to their corresponding image dimensions.
 
     The clamping is done according to the bounding boxes' ``canvas_size`` meta-data.
 
-    .. v2betastatus:: ClampBoundingBoxes transform
-
     """
 
     _transformed_types = (tv_tensors.BoundingBoxes,)

torchvision/transforms/v2/_misc.py

@@ -19,9 +19,7 @@ class Identity(Transform):
 
 
 class Lambda(Transform):
-    """[BETA] Apply a user-defined function as a transform.
-
-    .. v2betastatus:: Lambda transform
+    """Apply a user-defined function as a transform.
 
     This transform does not support torchscript.
 
@@ -52,9 +50,7 @@ class Lambda(Transform):
 
 
 class LinearTransformation(Transform):
-    """[BETA] Transform a tensor image or video with a square transformation matrix and a mean_vector computed offline.
-
-    .. v2betastatus:: LinearTransformation transform
+    """Transform a tensor image or video with a square transformation matrix and a mean_vector computed offline.
 
     This transform does not support PIL Image.
     Given transformation_matrix and mean_vector, will flatten the torch.*Tensor and
@@ -135,9 +131,7 @@ class LinearTransformation(Transform):
 
 
 class Normalize(Transform):
-    """[BETA] Normalize a tensor image or video with mean and standard deviation.
-
-    .. v2betastatus:: Normalize transform
+    """Normalize a tensor image or video with mean and standard deviation.
 
     This transform does not support PIL Image.
     Given mean: ``(mean[1],...,mean[n])`` and std: ``(std[1],..,std[n])`` for ``n``
@@ -172,9 +166,7 @@ class Normalize(Transform):
 
 
 class GaussianBlur(Transform):
-    """[BETA] Blurs image with randomly chosen Gaussian blur.
-
-    .. v2betastatus:: GausssianBlur transform
+    """Blurs image with randomly chosen Gaussian blur.
 
     If the input is a Tensor, it is expected
     to have [..., C, H, W] shape, where ... means an arbitrary number of leading dimensions.
@@ -212,9 +204,7 @@ class GaussianBlur(Transform):
 
 
 class ToDtype(Transform):
-    """[BETA] Converts the input to a specific dtype, optionally scaling the values for images or videos.
-
-    .. v2betastatus:: ToDtype transform
+    """Converts the input to a specific dtype, optionally scaling the values for images or videos.
 
     .. note::
         ``ToDtype(dtype, scale=True)`` is the recommended replacement for ``ConvertImageDtype(dtype)``.
@@ -286,12 +276,10 @@ class ToDtype(Transform):
 
 
 class ConvertImageDtype(Transform):
-    """[BETA] [DEPRECATED] Use ``v2.ToDtype(dtype, scale=True)`` instead.
+    """[DEPRECATED] Use ``v2.ToDtype(dtype, scale=True)`` instead.
 
     Convert input image to the given ``dtype`` and scale the values accordingly.
 
-    .. v2betastatus:: ConvertImageDtype transform
-
     .. warning::
         Consider using ``ToDtype(dtype, scale=True)`` instead. See :class:`~torchvision.transforms.v2.ToDtype`.
 
@@ -323,9 +311,7 @@ class ConvertImageDtype(Transform):
 
 
 class SanitizeBoundingBoxes(Transform):
-    """[BETA] Remove degenerate/invalid bounding boxes and their corresponding labels and masks.
-
-    .. v2betastatus:: SanitizeBoundingBoxes transform
+    """Remove degenerate/invalid bounding boxes and their corresponding labels and masks.
 
     This transform removes bounding boxes and their associated labels/masks that:
 

torchvision/transforms/v2/_temporal.py

@@ -5,9 +5,7 @@ from torchvision.transforms.v2 import functional as F, Transform
 
 
 class UniformTemporalSubsample(Transform):
-    """[BETA] Uniformly subsample ``num_samples`` indices from the temporal dimension of the video.
-
-    .. v2betastatus:: UniformTemporalSubsample transform
+    """Uniformly subsample ``num_samples`` indices from the temporal dimension of the video.
 
     Videos are expected to be of shape ``[..., T, C, H, W]`` where ``T`` denotes the temporal dimension.
 

torchvision/transforms/v2/_type_conversion.py

@@ -11,9 +11,7 @@ from torchvision.transforms.v2._utils import is_pure_tensor
 
 
 class PILToTensor(Transform):
-    """[BETA] Convert a PIL Image to a tensor of the same type - this does not scale values.
-
-    .. v2betastatus:: PILToTensor transform
+    """Convert a PIL Image to a tensor of the same type - this does not scale values.
 
     This transform does not support torchscript.
 
@@ -27,11 +25,9 @@ class PILToTensor(Transform):
 
 
 class ToImage(Transform):
-    """[BETA] Convert a tensor, ndarray, or PIL Image to :class:`~torchvision.tv_tensors.Image`
+    """Convert a tensor, ndarray, or PIL Image to :class:`~torchvision.tv_tensors.Image`
     ; this does not scale values.
 
-    .. v2betastatus:: ToImage transform
-
     This transform does not support torchscript.
     """
 
@@ -44,9 +40,7 @@ class ToImage(Transform):
 
 
 class ToPILImage(Transform):
-    """[BETA] Convert a tensor or an ndarray to PIL Image
-
-    .. v2betastatus:: ToPILImage transform
+    """Convert a tensor or an ndarray to PIL Image
 
     This transform does not support torchscript.
 
@@ -79,9 +73,7 @@ class ToPILImage(Transform):
 
 
 class ToPureTensor(Transform):
-    """[BETA] Convert all TVTensors to pure tensors, removing associated metadata (if any).
-
-    .. v2betastatus:: ToPureTensor transform
+    """Convert all TVTensors to pure tensors, removing associated metadata (if any).
 
     This doesn't scale or change the values, only the type.
     """

torchvision/transforms/v2/functional/_augment.py

@@ -17,7 +17,7 @@ def erase(
     v: torch.Tensor,
     inplace: bool = False,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomErase` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomErase` for details."""
     if torch.jit.is_scripting():
         return erase_image(inpt, i=i, j=j, h=h, w=w, v=v, inplace=inplace)
 

torchvision/transforms/v2/functional/_color.py

@@ -15,7 +15,7 @@ from ._utils import _get_kernel, _register_kernel_internal
 
 
 def rgb_to_grayscale(inpt: torch.Tensor, num_output_channels: int = 1) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.Grayscale` for details."""
+    """See :class:`~torchvision.transforms.v2.Grayscale` for details."""
     if torch.jit.is_scripting():
         return rgb_to_grayscale_image(inpt, num_output_channels=num_output_channels)
 
@@ -147,7 +147,7 @@ def adjust_saturation_video(video: torch.Tensor, saturation_factor: float) -> to
 
 
 def adjust_contrast(inpt: torch.Tensor, contrast_factor: float) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.RandomAutocontrast`"""
+    """See :class:`~torchvision.transforms.RandomAutocontrast`"""
     if torch.jit.is_scripting():
         return adjust_contrast_image(inpt, contrast_factor=contrast_factor)
 
@@ -186,7 +186,7 @@ def adjust_contrast_video(video: torch.Tensor, contrast_factor: float) -> torch.
 
 
 def adjust_sharpness(inpt: torch.Tensor, sharpness_factor: float) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.RandomAdjustSharpness`"""
+    """See :class:`~torchvision.transforms.RandomAdjustSharpness`"""
     if torch.jit.is_scripting():
         return adjust_sharpness_image(inpt, sharpness_factor=sharpness_factor)
 
@@ -417,7 +417,7 @@ def adjust_gamma_video(video: torch.Tensor, gamma: float, gain: float = 1) -> to
 
 
 def posterize(inpt: torch.Tensor, bits: int) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomPosterize` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomPosterize` for details."""
     if torch.jit.is_scripting():
         return posterize_image(inpt, bits=bits)
 
@@ -451,7 +451,7 @@ def posterize_video(video: torch.Tensor, bits: int) -> torch.Tensor:
 
 
 def solarize(inpt: torch.Tensor, threshold: float) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomSolarize` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomSolarize` for details."""
     if torch.jit.is_scripting():
         return solarize_image(inpt, threshold=threshold)
 
@@ -479,7 +479,7 @@ def solarize_video(video: torch.Tensor, threshold: float) -> torch.Tensor:
 
 
 def autocontrast(inpt: torch.Tensor) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomAutocontrast` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomAutocontrast` for details."""
     if torch.jit.is_scripting():
         return autocontrast_image(inpt)
 
@@ -529,7 +529,7 @@ def autocontrast_video(video: torch.Tensor) -> torch.Tensor:
 
 
 def equalize(inpt: torch.Tensor) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomEqualize` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomEqualize` for details."""
     if torch.jit.is_scripting():
         return equalize_image(inpt)
 
@@ -619,7 +619,7 @@ def equalize_video(video: torch.Tensor) -> torch.Tensor:
 
 
 def invert(inpt: torch.Tensor) -> torch.Tensor:
-    """[BETA] See :func:`~torchvision.transforms.v2.RandomInvert`."""
+    """See :func:`~torchvision.transforms.v2.RandomInvert`."""
     if torch.jit.is_scripting():
         return invert_image(inpt)
 

torchvision/transforms/v2/functional/_deprecated.py

@@ -8,7 +8,7 @@ from torchvision.transforms import functional as _F
 
 @torch.jit.unused
 def to_tensor(inpt: Any) -> torch.Tensor:
-    """[BETA] [DEPREACTED] Use to_image() and to_dtype() instead."""
+    """[DEPREACTED] Use to_image() and to_dtype() instead."""
     warnings.warn(
         "The function `to_tensor(...)` is deprecated and will be removed in a future release. "
         "Instead, please use `to_image(...)` followed by `to_dtype(..., dtype=torch.float32, scale=True)`."

torchvision/transforms/v2/functional/_geometry.py

@@ -39,7 +39,7 @@ def _check_interpolation(interpolation: Union[InterpolationMode, int]) -> Interp
 
 
 def horizontal_flip(inpt: torch.Tensor) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomHorizontalFlip` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomHorizontalFlip` for details."""
     if torch.jit.is_scripting():
         return horizontal_flip_image(inpt)
 
@@ -96,7 +96,7 @@ def horizontal_flip_video(video: torch.Tensor) -> torch.Tensor:
 
 
 def vertical_flip(inpt: torch.Tensor) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomVerticalFlip` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomVerticalFlip` for details."""
     if torch.jit.is_scripting():
         return vertical_flip_image(inpt)
 
@@ -178,7 +178,7 @@ def resize(
     max_size: Optional[int] = None,
     antialias: Optional[bool] = True,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.Resize` for details."""
+    """See :class:`~torchvision.transforms.v2.Resize` for details."""
     if torch.jit.is_scripting():
         return resize_image(inpt, size=size, interpolation=interpolation, max_size=max_size, antialias=antialias)
 
@@ -373,7 +373,7 @@ def affine(
     fill: _FillTypeJIT = None,
     center: Optional[List[float]] = None,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomAffine` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomAffine` for details."""
     if torch.jit.is_scripting():
         return affine_image(
             inpt,
@@ -939,7 +939,7 @@ def rotate(
     center: Optional[List[float]] = None,
     fill: _FillTypeJIT = None,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomRotation` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomRotation` for details."""
     if torch.jit.is_scripting():
         return rotate_image(inpt, angle=angle, interpolation=interpolation, expand=expand, fill=fill, center=center)
 
@@ -1094,7 +1094,7 @@ def pad(
     fill: Optional[Union[int, float, List[float]]] = None,
     padding_mode: str = "constant",
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.Pad` for details."""
+    """See :class:`~torchvision.transforms.v2.Pad` for details."""
     if torch.jit.is_scripting():
         return pad_image(inpt, padding=padding, fill=fill, padding_mode=padding_mode)
 
@@ -1314,7 +1314,7 @@ def pad_video(
 
 
 def crop(inpt: torch.Tensor, top: int, left: int, height: int, width: int) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomCrop` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomCrop` for details."""
     if torch.jit.is_scripting():
         return crop_image(inpt, top=top, left=left, height=height, width=width)
 
@@ -1408,7 +1408,7 @@ def perspective(
     fill: _FillTypeJIT = None,
     coefficients: Optional[List[float]] = None,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomPerspective` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomPerspective` for details."""
     if torch.jit.is_scripting():
         return perspective_image(
             inpt,
@@ -1696,7 +1696,7 @@ def elastic(
     interpolation: Union[InterpolationMode, int] = InterpolationMode.BILINEAR,
     fill: _FillTypeJIT = None,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.ElasticTransform` for details."""
+    """See :class:`~torchvision.transforms.v2.ElasticTransform` for details."""
     if torch.jit.is_scripting():
         return elastic_image(inpt, displacement=displacement, interpolation=interpolation, fill=fill)
 
@@ -1880,7 +1880,7 @@ def elastic_video(
 
 
 def center_crop(inpt: torch.Tensor, output_size: List[int]) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomCrop` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomCrop` for details."""
     if torch.jit.is_scripting():
         return center_crop_image(inpt, output_size=output_size)
 
@@ -2009,7 +2009,7 @@ def resized_crop(
     interpolation: Union[InterpolationMode, int] = InterpolationMode.BILINEAR,
     antialias: Optional[bool] = True,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.RandomResizedCrop` for details."""
+    """See :class:`~torchvision.transforms.v2.RandomResizedCrop` for details."""
     if torch.jit.is_scripting():
         return resized_crop_image(
             inpt,
@@ -2154,7 +2154,7 @@ def resized_crop_video(
 def five_crop(
     inpt: torch.Tensor, size: List[int]
 ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor]:
-    """[BETA] See :class:`~torchvision.transforms.v2.FiveCrop` for details."""
+    """See :class:`~torchvision.transforms.v2.FiveCrop` for details."""
     if torch.jit.is_scripting():
         return five_crop_image(inpt, size=size)
 
@@ -2238,7 +2238,7 @@ def ten_crop(
     torch.Tensor,
     torch.Tensor,
 ]:
-    """[BETA] See :class:`~torchvision.transforms.v2.TenCrop` for details."""
+    """See :class:`~torchvision.transforms.v2.TenCrop` for details."""
     if torch.jit.is_scripting():
         return ten_crop_image(inpt, size=size, vertical_flip=vertical_flip)
 

torchvision/transforms/v2/functional/_meta.py

@@ -203,7 +203,7 @@ def convert_bounding_box_format(
     new_format: Optional[BoundingBoxFormat] = None,
     inplace: bool = False,
 ) -> torch.Tensor:
-    """[BETA] See :func:`~torchvision.transforms.v2.ConvertBoundingBoxFormat` for details."""
+    """See :func:`~torchvision.transforms.v2.ConvertBoundingBoxFormat` for details."""
     # This being a kernel / functional hybrid, we need an option to pass `old_format` explicitly for pure tensor
     # inputs as well as extract it from `tv_tensors.BoundingBoxes` inputs. However, putting a default value on
     # `old_format` means we also need to put one on `new_format` to have syntactically correct Python. Here we mimic the
@@ -254,7 +254,7 @@ def clamp_bounding_boxes(
     format: Optional[BoundingBoxFormat] = None,
     canvas_size: Optional[Tuple[int, int]] = None,
 ) -> torch.Tensor:
-    """[BETA] See :func:`~torchvision.transforms.v2.ClampBoundingBoxes` for details."""
+    """See :func:`~torchvision.transforms.v2.ClampBoundingBoxes` for details."""
     if not torch.jit.is_scripting():
         _log_api_usage_once(clamp_bounding_boxes)
 

torchvision/transforms/v2/functional/_misc.py

@@ -20,7 +20,7 @@ def normalize(
     std: List[float],
     inplace: bool = False,
 ) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.Normalize` for details."""
+    """See :class:`~torchvision.transforms.v2.Normalize` for details."""
     if torch.jit.is_scripting():
         return normalize_image(inpt, mean=mean, std=std, inplace=inplace)
 
@@ -71,7 +71,7 @@ def normalize_video(video: torch.Tensor, mean: List[float], std: List[float], in
 
 
 def gaussian_blur(inpt: torch.Tensor, kernel_size: List[int], sigma: Optional[List[float]] = None) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.GaussianBlur` for details."""
+    """See :class:`~torchvision.transforms.v2.GaussianBlur` for details."""
     if torch.jit.is_scripting():
         return gaussian_blur_image(inpt, kernel_size=kernel_size, sigma=sigma)
 
@@ -180,7 +180,7 @@ def gaussian_blur_video(
 
 
 def to_dtype(inpt: torch.Tensor, dtype: torch.dtype = torch.float, scale: bool = False) -> torch.Tensor:
-    """[BETA] See :func:`~torchvision.transforms.v2.ToDtype` for details."""
+    """See :func:`~torchvision.transforms.v2.ToDtype` for details."""
     if torch.jit.is_scripting():
         return to_dtype_image(inpt, dtype=dtype, scale=scale)
 
@@ -261,7 +261,7 @@ def to_dtype_image(image: torch.Tensor, dtype: torch.dtype = torch.float, scale:
 
 # We encourage users to use to_dtype() instead but we keep this for BC
 def convert_image_dtype(image: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
-    """[BETA] [DEPRECATED] Use to_dtype() instead."""
+    """[DEPRECATED] Use to_dtype() instead."""
     return to_dtype_image(image, dtype=dtype, scale=True)
 
 

torchvision/transforms/v2/functional/_temporal.py

@@ -8,7 +8,7 @@ from ._utils import _get_kernel, _register_kernel_internal
 
 
 def uniform_temporal_subsample(inpt: torch.Tensor, num_samples: int) -> torch.Tensor:
-    """[BETA] See :class:`~torchvision.transforms.v2.UniformTemporalSubsample` for details."""
+    """See :class:`~torchvision.transforms.v2.UniformTemporalSubsample` for details."""
     if torch.jit.is_scripting():
         return uniform_temporal_subsample_video(inpt, num_samples=num_samples)
 

torchvision/transforms/v2/functional/_type_conversion.py

@@ -9,7 +9,7 @@ from torchvision.transforms import functional as _F
 
 @torch.jit.unused
 def to_image(inpt: Union[torch.Tensor, PIL.Image.Image, np.ndarray]) -> tv_tensors.Image:
-    """[BETA] See :class:`~torchvision.transforms.v2.ToImage` for details."""
+    """See :class:`~torchvision.transforms.v2.ToImage` for details."""
     if isinstance(inpt, np.ndarray):
         output = torch.from_numpy(inpt).permute((2, 0, 1)).contiguous()
     elif isinstance(inpt, PIL.Image.Image):