Merge branch 'main' into arm-adjust-hue-fix

.github/workflows/build-wheels-windows.yml

@@ -25,6 +25,7 @@ jobs:
       os: windows
       test-infra-repository: pytorch/test-infra
       test-infra-ref: main
+      with-xpu: enable
   build:
     needs: generate-matrix
     strategy:

README.md

@@ -21,6 +21,7 @@ versions.
 | `torch`            | `torchvision`      | Python              |
 | ------------------ | ------------------ | ------------------- |
 | `main` / `nightly` | `main` / `nightly` | `>=3.9`, `<=3.12`   |
+| `2.5`              | `0.20`             | `>=3.9`, `<=3.12`   |
 | `2.4`              | `0.19`             | `>=3.8`, `<=3.12`   |
 | `2.3`              | `0.18`             | `>=3.8`, `<=3.12`   |
 | `2.2`              | `0.17`             | `>=3.8`, `<=3.11`   |

docs/source/io.rst

@@ -3,46 +3,98 @@ Decoding / Encoding images and videos
 
 .. currentmodule:: torchvision.io
 
-The :mod:`torchvision.io` package provides functions for performing IO
-operations. They are currently specific to reading and writing images and
-videos.
+The :mod:`torchvision.io` module provides utilities for decoding and encoding
+images and videos.
 
-Images
-------
+Image Decoding
+--------------
 
 Torchvision currently supports decoding JPEG, PNG, WEBP and GIF images. JPEG
 decoding can also be done on CUDA GPUs.
 
-For encoding, JPEG (cpu and CUDA) and PNG are supported.
+The main entry point is the :func:`~torchvision.io.decode_image` function, which
+you can use as an alternative to ``PIL.Image.open()``. It will decode images
+straight into image Tensors, thus saving you the conversion and allowing you to
+run transforms/preproc natively on tensors.
+
+.. code::
+
+    from torchvision.io import decode_image
+
+    img = decode_image("path_to_image", mode="RGB")
+    img.dtype  # torch.uint8
+
+    # Or
+    raw_encoded_bytes = ...  # read encoded bytes from your file system
+    img = decode_image(raw_encoded_bytes, mode="RGB")
+
+
+:func:`~torchvision.io.decode_image` will automatically detect the image format,
+and call the corresponding decoder. You can also use the lower-level
+format-specific decoders which can be more powerful, e.g. if you want to
+encode/decode JPEGs on CUDA.
 
 .. autosummary::
     :toctree: generated/
     :template: function.rst
 
-    read_image
     decode_image
-    encode_jpeg
     decode_jpeg
-    write_jpeg
+    encode_png
     decode_gif
     decode_webp
-    encode_png
-    decode_png
-    write_png
-    read_file
-    write_file
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
     ImageReadMode
 
+Obsolete decoding function:
 
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    read_image
+
+Image Encoding
+--------------
+
+For encoding, JPEG (cpu and CUDA) and PNG are supported.
+
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    encode_jpeg
+    write_jpeg
+    encode_png
+    write_png
+
+IO operations
+-------------
+
+.. autosummary::
+    :toctree: generated/
+    :template: function.rst
+
+    read_file
+    write_file
 
 Video
 -----
 
+.. warning::
+
+    Torchvision supports video decoding through different APIs listed below,
+    some of which are still in BETA stage. In the near future, we intend to
+    centralize PyTorch's video decoding capabilities within the `torchcodec
+    <https://github.com/pytorch/torchcodec>`_ project. We encourage you to try
+    it out and share your feedback, as the torchvision video decoders will
+    eventually be deprecated.
+
 .. autosummary::
     :toctree: generated/
     :template: function.rst
@@ -52,45 +104,14 @@ Video
     write_video
 
 
-Fine-grained video API
-^^^^^^^^^^^^^^^^^^^^^^
+**Fine-grained video API**
 
 In addition to the :mod:`read_video` function, we provide a high-performance 
 lower-level API for more fine-grained control compared to the :mod:`read_video` function.
 It does all this whilst fully supporting torchscript.
 
-.. betastatus:: fine-grained video API
-
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
     VideoReader
-
-
-Example of inspecting a video:
-
-.. code:: python
-
-    import torchvision
-    video_path = "path to a test video"
-    # Constructor allocates memory and a threaded decoder
-    # instance per video. At the moment it takes two arguments:
-    # path to the video file, and a wanted stream.
-    reader = torchvision.io.VideoReader(video_path, "video")
-
-    # The information about the video can be retrieved using the 
-    # `get_metadata()` method. It returns a dictionary for every stream, with
-    # duration and other relevant metadata (often frame rate)
-    reader_md = reader.get_metadata()
-
-    # metadata is structured as a dict of dicts with following structure
-    # {"stream_type": {"attribute": [attribute per stream]}}
-    #
-    # following would print out the list of frame rates for every present video stream
-    print(reader_md["video"]["fps"])
-
-    # we explicitly select the stream we would like to operate on. In
-    # the constructor we select a default video stream, but
-    # in practice, we can set whichever stream we would like 
-    video.set_current_stream("video:0")

docs/source/models.rst

@@ -226,10 +226,10 @@ Here is an example of how to use the pre-trained image classification models:
 
 .. code:: python
 
-    from torchvision.io import read_image
+    from torchvision.io import decode_image
     from torchvision.models import resnet50, ResNet50_Weights
 
-    img = read_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
+    img = decode_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
 
     # Step 1: Initialize model with the best available weights
     weights = ResNet50_Weights.DEFAULT
@@ -283,10 +283,10 @@ Here is an example of how to use the pre-trained quantized image classification
 
 .. code:: python
 
-    from torchvision.io import read_image
+    from torchvision.io import decode_image
     from torchvision.models.quantization import resnet50, ResNet50_QuantizedWeights
 
-    img = read_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
+    img = decode_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
 
     # Step 1: Initialize model with the best available weights
     weights = ResNet50_QuantizedWeights.DEFAULT
@@ -339,11 +339,11 @@ Here is an example of how to use the pre-trained semantic segmentation models:
 
 .. code:: python
 
-    from torchvision.io.image import read_image
+    from torchvision.io.image import decode_image
     from torchvision.models.segmentation import fcn_resnet50, FCN_ResNet50_Weights
     from torchvision.transforms.functional import to_pil_image
 
-    img = read_image("gallery/assets/dog1.jpg")
+    img = decode_image("gallery/assets/dog1.jpg")
 
     # Step 1: Initialize model with the best available weights
     weights = FCN_ResNet50_Weights.DEFAULT
@@ -411,12 +411,12 @@ Here is an example of how to use the pre-trained object detection models:
 .. code:: python
 
 
-    from torchvision.io.image import read_image
+    from torchvision.io.image import decode_image
     from torchvision.models.detection import fasterrcnn_resnet50_fpn_v2, FasterRCNN_ResNet50_FPN_V2_Weights
     from torchvision.utils import draw_bounding_boxes
     from torchvision.transforms.functional import to_pil_image
 
-    img = read_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
+    img = decode_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")
 
     # Step 1: Initialize model with the best available weights
     weights = FasterRCNN_ResNet50_FPN_V2_Weights.DEFAULT

gallery/others/plot_repurposing_annotations.py

@@ -66,12 +66,12 @@ def show(imgs):
 # We will take images and masks from the `PenFudan Dataset <https://www.cis.upenn.edu/~jshi/ped_html/>`_.
 
 
-from torchvision.io import read_image
+from torchvision.io import decode_image
 
 img_path = os.path.join(ASSETS_DIRECTORY, "FudanPed00054.png")
 mask_path = os.path.join(ASSETS_DIRECTORY, "FudanPed00054_mask.png")
-img = read_image(img_path)
-mask = read_image(mask_path)
+img = decode_image(img_path)
+mask = decode_image(mask_path)
 
 
 # %%
@@ -181,8 +181,8 @@ def __getitem__(self, idx):
         img_path = os.path.join(self.root, "PNGImages", self.imgs[idx])
         mask_path = os.path.join(self.root, "PedMasks", self.masks[idx])
 
-        img = read_image(img_path)
-        mask = read_image(mask_path)
+        img = decode_image(img_path)
+        mask = decode_image(mask_path)
 
         img = F.convert_image_dtype(img, dtype=torch.float)
         mask = F.convert_image_dtype(mask, dtype=torch.float)

gallery/others/plot_scripted_tensor_transforms.py

@@ -21,7 +21,7 @@
 import torch.nn as nn
 
 import torchvision.transforms as v1
-from torchvision.io import read_image
+from torchvision.io import decode_image
 
 plt.rcParams["savefig.bbox"] = 'tight'
 torch.manual_seed(1)
@@ -39,8 +39,8 @@
 # :class:`torch.nn.Sequential` instead of
 # :class:`~torchvision.transforms.v2.Compose`:
 
-dog1 = read_image(str(ASSETS_PATH / 'dog1.jpg'))
-dog2 = read_image(str(ASSETS_PATH / 'dog2.jpg'))
+dog1 = decode_image(str(ASSETS_PATH / 'dog1.jpg'))
+dog2 = decode_image(str(ASSETS_PATH / 'dog2.jpg'))
 
 transforms = torch.nn.Sequential(
     v1.RandomCrop(224),

gallery/others/plot_visualization_utils.py

@@ -42,11 +42,11 @@ def show(imgs):
 # image of dtype ``uint8`` as input.
 
 from torchvision.utils import make_grid
-from torchvision.io import read_image
+from torchvision.io import decode_image
 from pathlib import Path
 
-dog1_int = read_image(str(Path('../assets') / 'dog1.jpg'))
-dog2_int = read_image(str(Path('../assets') / 'dog2.jpg'))
+dog1_int = decode_image(str(Path('../assets') / 'dog1.jpg'))
+dog2_int = decode_image(str(Path('../assets') / 'dog2.jpg'))
 dog_list = [dog1_int, dog2_int]
 
 grid = make_grid(dog_list)
@@ -362,9 +362,9 @@ def show(imgs):
 #
 
 from torchvision.models.detection import keypointrcnn_resnet50_fpn, KeypointRCNN_ResNet50_FPN_Weights
-from torchvision.io import read_image
+from torchvision.io import decode_image
 
-person_int = read_image(str(Path("../assets") / "person1.jpg"))
+person_int = decode_image(str(Path("../assets") / "person1.jpg"))
 
 weights = KeypointRCNN_ResNet50_FPN_Weights.DEFAULT
 transforms = weights.transforms()

gallery/transforms/plot_transforms_getting_started.py

@@ -21,14 +21,14 @@
 plt.rcParams["savefig.bbox"] = 'tight'
 
 from torchvision.transforms import v2
-from torchvision.io import read_image
+from torchvision.io import decode_image
 
 torch.manual_seed(1)
 
 # If you're trying to run that on Colab, you can download the assets and the
 # helpers from https://github.com/pytorch/vision/tree/main/gallery/
 from helpers import plot
-img = read_image(str(Path('../assets') / 'astronaut.jpg'))
+img = decode_image(str(Path('../assets') / 'astronaut.jpg'))
 print(f"{type(img) = }, {img.dtype = }, {img.shape = }")
 
 # %%

packaging/windows/internal/vc_env_helper.bat

@@ -28,6 +28,8 @@ if "%VSDEVCMD_ARGS%" == "" (
 
 @echo on
 
+if "%CU_VERSION%" == "xpu" call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat"
+
 set DISTUTILS_USE_SDK=1
 
 set args=%1