Merge branch 'main' into main

Author: Alexandre-SCHOEPP

.github/workflows/build-wheels-aarch64-linux.yml

@@ -25,7 +25,7 @@ jobs:
       os: linux-aarch64
       test-infra-repository: pytorch/test-infra
       test-infra-ref: main
-      with-cuda: disable
+      with-cuda: enable
   build:
     needs: generate-matrix
     strategy:

docs/source/training_references.rst

@@ -19,9 +19,9 @@ guarantees.
 
 In general, these scripts rely on the latest (not yet released) pytorch version
 or the latest torchvision version. This means that to use them, **you might need
-to install the latest pytorch and torchvision versions**, with e.g.::
+to install the latest pytorch and torchvision versions** following the `official
+instructions <https://pytorch.org/get-started/locally/>`_.
 
-    conda install pytorch torchvision -c pytorch-nightly
 
 If you need to rely on an older stable version of pytorch or torchvision, e.g.
 torchvision 0.10, then it's safer to use the scripts from that corresponding

packaging/pre_build_script_arm64.sh

@@ -0,0 +1,69 @@
+#!/bin/bash
+
+echo "Building vision dependencies and wheel started."
+
+# Set environment variables
+export SRC_PATH="$GITHUB_WORKSPACE/$SRC_DIR"
+export CMAKE_BUILD_TYPE="$BUILD_TYPE"
+export VCVARSALL_PATH="$DEPENDENCIES_DIR/VSBuildTools/VC/Auxiliary/Build/vcvarsall.bat"
+export CONDA_PREFIX="$DEPENDENCIES_DIR"
+export PATH="$PATH:$CONDA_PREFIX/Library/bin"
+export DISTUTILS_USE_SDK=1
+export TRIPLET_FILE="triplets/arm64-windows.cmake"
+export PYTORCH_VERSION="$PYTORCH_VERSION"
+export CHANNEL="$CHANNEL"
+
+# Dependencies
+mkdir -p "$DOWNLOADS_DIR"
+mkdir -p "$DEPENDENCIES_DIR"
+echo "*" > "$DOWNLOADS_DIR/.gitignore"
+echo "*" > "$DEPENDENCIES_DIR/.gitignore"
+
+# Install vcpkg
+cd "$DOWNLOADS_DIR" || exit
+git clone https://github.com/microsoft/vcpkg.git
+cd vcpkg || exit
+./bootstrap-vcpkg.sh
+
+# Set vcpkg to only build release packages
+echo "set(VCPKG_BUILD_TYPE release)" >> "$TRIPLET_FILE"
+
+# Install dependencies using vcpkg
+./vcpkg install libjpeg-turbo:arm64-windows --x-install-root="$DEPENDENCIES_DIR"
+./vcpkg install libwebp:arm64-windows --x-install-root="$DEPENDENCIES_DIR"
+./vcpkg install libpng[tools]:arm64-windows --x-install-root="$DEPENDENCIES_DIR"
+
+# Copy files using cp
+cp "$DEPENDENCIES_DIR/arm64-windows/lib/libpng16.lib" "$DEPENDENCIES_DIR/arm64-windows/lib/libpng.lib"
+cp "$DEPENDENCIES_DIR/arm64-windows/bin/libpng16.dll" "$DEPENDENCIES_DIR/arm64-windows/bin/libpng.dll"
+cp "$DEPENDENCIES_DIR/arm64-windows/bin/libpng16.pdb" "$DEPENDENCIES_DIR/arm64-windows/bin/libpng.pdb"
+mkdir -p "$DEPENDENCIES_DIR/Library/"
+cp -r "$DEPENDENCIES_DIR/arm64-windows/"* "$DEPENDENCIES_DIR/Library/"
+cp -r "$DEPENDENCIES_DIR/Library/tools/libpng/"* "$DEPENDENCIES_DIR/Library/bin/"
+cp -r "$DEPENDENCIES_DIR/Library/bin/"* "$SRC_PATH/torchvision"
+
+# Source directory
+cd "$SRC_PATH" || exit
+
+# Create virtual environment
+python -m pip install --upgrade pip
+python -m venv .venv
+echo "*" > .venv/.gitignore
+source .venv/Scripts/activate
+
+# Install dependencies
+pip install numpy==2.2.3
+
+if [ "$CHANNEL" = "release" ]; then
+  echo "Installing latest stable version of PyTorch."
+  # TODO: update when arm64 torch available on pypi
+  pip3 install --pre torch --index-url https://download.pytorch.org/whl/torch/
+elif [ "$CHANNEL" = "test" ]; then
+  echo "Installing PyTorch version $PYTORCH_VERSION."
+  pip3 install --pre torch=="$PYTORCH_VERSION" --index-url https://download.pytorch.org/whl/test
+else
+  echo "CHANNEL is not set, installing PyTorch from nightly."
+  pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/cpu
+fi
+
+echo "Dependencies install finished successfully."

setup.py

@@ -24,7 +24,7 @@
 NVCC_FLAGS = os.getenv("NVCC_FLAGS", None)
 # Note: the GPU video decoding stuff used to be called "video codec", which
 # isn't an accurate or descriptive name considering there are at least 2 other
-# video deocding backends in torchvision. I'm renaming this to "gpu video
+# video decoding backends in torchvision. I'm renaming this to "gpu video
 # decoder" where possible, keeping user facing names (like the env var below) to
 # the old scheme for BC.
 USE_GPU_VIDEO_DECODER = os.getenv("TORCHVISION_USE_VIDEO_CODEC", "1") == "1"
@@ -211,7 +211,7 @@ def find_libpng():
             subprocess.run([libpng_config, "--version"], stdout=subprocess.PIPE).stdout.strip().decode("utf-8")
         )
         if png_version < min_version:
-            warnings.warn("libpng version {png_version} is less than minimum required version {min_version}")
+            warnings.warn(f"libpng version {png_version} is less than minimum required version {min_version}")
             return False, None, None, None
 
         include_dir = (
@@ -448,7 +448,7 @@ def find_ffmpeg_libraries():
 
         extensions.append(
             CppExtension(
-                # This is an aweful name. It should be "cpu_video_decoder". Keeping for BC.
+                # This is an awful name. It should be "cpu_video_decoder". Keeping for BC.
                 "torchvision.video_reader",
                 combined_src,
                 include_dirs=[

torchvision/datasets/lfw.py

@@ -51,6 +51,10 @@ def __init__(
         self.data: list[Any] = []
 
         if download:
+            raise ValueError(
+                "LFW dataset is no longer available for download."
+                "Please download the dataset manually and place it in the specified directory"
+            )
             self.download()
 
         if not self._check_integrity():
@@ -90,6 +94,11 @@ def __len__(self) -> int:
 class LFWPeople(_LFW):
     """`LFW <http://vis-www.cs.umass.edu/lfw/>`_ Dataset.
 
+    .. warning:
+
+        The LFW dataset is no longer available for automatic download. Please
+        download it manually and place it in the specified directory.
+
     Args:
         root (str or ``pathlib.Path``): Root directory of dataset where directory
             ``lfw-py`` exists or will be saved to if download is set to True.
@@ -101,9 +110,7 @@ class LFWPeople(_LFW):
             and returns a transformed version. E.g, ``transforms.RandomCrop``
         target_transform (callable, optional): A function/transform that takes in the
             target and transforms it.
-        download (bool, optional): If true, downloads the dataset from the internet and
-            puts it in root directory. If dataset is already downloaded, it is not
-            downloaded again.
+        download (bool, optional): NOT SUPPORTED ANYMORE, leave to False.
         loader (callable, optional): A function to load an image given its path.
             By default, it uses PIL as its image loader, but users could also pass in
             ``torchvision.io.decode_image`` for decoding image data into tensors directly.
@@ -175,6 +182,11 @@ def extra_repr(self) -> str:
 class LFWPairs(_LFW):
     """`LFW <http://vis-www.cs.umass.edu/lfw/>`_ Dataset.
 
+    .. warning:
+
+        The LFW dataset is no longer available for automatic download. Please
+        download it manually and place it in the specified directory.
+
     Args:
         root (str or ``pathlib.Path``): Root directory of dataset where directory
             ``lfw-py`` exists or will be saved to if download is set to True.
@@ -186,9 +198,7 @@ class LFWPairs(_LFW):
             and returns a transformed version. E.g, ``transforms.RandomRotation``
         target_transform (callable, optional): A function/transform that takes in the
             target and transforms it.
-        download (bool, optional): If true, downloads the dataset from the internet and
-            puts it in root directory. If dataset is already downloaded, it is not
-            downloaded again.
+        download (bool, optional): NOT SUPPORTED ANYMORE, leave to False.
         loader (callable, optional): A function to load an image given its path.
             By default, it uses PIL as its image loader, but users could also pass in
             ``torchvision.io.decode_image`` for decoding image data into tensors directly.

torchvision/models/detection/mask_rcnn.py

@@ -50,7 +50,7 @@ class MaskRCNN(FasterRCNN):
           ``0 <= x1 < x2 <= W`` and ``0 <= y1 < y2 <= H``.
         - labels (Int64Tensor[N]): the predicted labels for each image
         - scores (Tensor[N]): the scores or each prediction
-        - masks (UInt8Tensor[N, 1, H, W]): the predicted masks for each instance, in 0-1 range. In order to
+        - masks (FloatTensor[N, 1, H, W]): the predicted masks for each instance, in 0-1 range. In order to
           obtain the final segmentation masks, the soft masks can be thresholded, generally
           with a value of 0.5 (mask >= 0.5)
 

version.txt

@@ -1 +1 @@
-0.22.0a0
+0.23.0a0