2023-11-14 nightly release (9fa5f3f)

docs/source/beta_status.py

@@ -12,18 +12,8 @@ def run(self):
         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

@@ -103,7 +103,9 @@ V1 or V2? Which one should I use?
 
 **TL;DR** We recommending using the ``torchvision.transforms.v2`` transforms
 instead of those in ``torchvision.transforms``. They're faster and they can do
-more things. Just change the import and you should be good to go.
+more things. Just change the import and you should be good to go. Moving
+forward, new features and improvements will only be considered for the v2
+transforms.
 
 In Torchvision 0.15 (March 2023), we released a new set of transforms available
 in the ``torchvision.transforms.v2`` namespace. These transforms have a lot of
@@ -126,13 +128,6 @@ 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

test/test_transforms.py

@@ -2,7 +2,6 @@
 import os
 import random
 import re
-import textwrap
 from functools import partial
 
 import numpy as np
@@ -24,7 +23,7 @@
 except ImportError:
     stats = None
 
-from common_utils import assert_equal, assert_run_python_script, cycle_over, float_dtypes, int_dtypes
+from common_utils import assert_equal, cycle_over, float_dtypes, int_dtypes
 
 
 GRACE_HOPPER = get_file_path_2(
@@ -2241,35 +2240,5 @@ def test_random_grayscale_with_grayscale_input():
     torch.testing.assert_close(F.pil_to_tensor(output_pil), image_tensor)
 
 
-# TODO: remove in 0.17 when we can delete functional_pil.py and functional_tensor.py
-@pytest.mark.parametrize(
-    "import_statement",
-    (
-        "from torchvision.transforms import functional_pil",
-        "from torchvision.transforms import functional_tensor",
-        "from torchvision.transforms.functional_tensor import resize",
-        "from torchvision.transforms.functional_pil import resize",
-    ),
-)
-@pytest.mark.parametrize("from_private", (True, False))
-def test_functional_deprecation_warning(import_statement, from_private):
-    if from_private:
-        import_statement = import_statement.replace("functional", "_functional")
-        source = f"""
-        import warnings
-
-        with warnings.catch_warnings():
-            warnings.simplefilter("error")
-            {import_statement}
-        """
-    else:
-        source = f"""
-        import pytest
-        with pytest.warns(UserWarning, match="removed in 0.17"):
-            {import_statement}
-        """
-    assert_run_python_script(textwrap.dedent(source))
-
-
 if __name__ == "__main__":
     pytest.main([__file__])

torchvision/datasets/video_utils.py

@@ -136,7 +136,7 @@ def __init__(
 
     def _compute_frame_pts(self) -> None:
         self.video_pts = []
-        self.video_fps = []
+        self.video_fps: List[int] = []
 
         # strategy: use a DataLoader to parallelize read_video_timestamps
         # so need to create a dummy dataset first

torchvision/transforms/v2/_augment.py

@@ -15,9 +15,7 @@
 
 
 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 @@ def _mixup_label(self, label: torch.Tensor, *, lam: float) -> torch.Tensor:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _apply_image_or_video_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 @@ def forward(self, *inputs: Any) -> Any:
 
 
 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 @@ def forward(self, *inputs: Any) -> Any:
 
 
 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 @@ def forward(self, *inputs: Any) -> Any:
 
 
 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 @@
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@ def _transform(self, inpt: Any, params: Dict[str, Any]) -> Any:
 
 
 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 @@
 
 
 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 @@ def extra_repr(self) -> str:
 
 
 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 @@ def extra_repr(self) -> str:
 
 
 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 @@ def forward(self, *inputs: Any) -> Any:
 
 
 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.