Merge branch 'main' into fix/voc_download

Author: GdoongMathew

.github/workflows/build-cmake.yml

@@ -18,7 +18,7 @@ jobs:
             gpu-arch-type: cpu
           - runner: linux.g5.4xlarge.nvidia.gpu
             gpu-arch-type: cuda
-            gpu-arch-version: "11.8"
+            gpu-arch-version: "12.6"
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:
@@ -66,7 +66,7 @@ jobs:
             gpu-arch-type: cpu
           - runner: windows.g5.4xlarge.nvidia.gpu
             gpu-arch-type: cuda
-            gpu-arch-version: "11.8"
+            gpu-arch-version: "12.6"
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/windows_job.yml@main
     with:

.github/workflows/build_wheel_windows_arm64.yml

@@ -0,0 +1,54 @@
+name: Build Windows ARM64 Wheels
+
+on:
+  pull_request:
+    paths:
+      - .github/workflows/build_wheel_windows_arm64.yml
+  push:
+    branches:
+      - nightly
+      - release/*
+    tags:
+        # NOTE: Binary build pipelines should only get triggered on release candidate builds
+        # Release candidate tags look like: v1.11.0-rc1
+        - v[0-9]+.[0-9]+.[0-9]+-rc[0-9]+
+  workflow_dispatch:
+
+permissions:
+  id-token: write
+  contents: read
+
+jobs:
+  generate-matrix:
+    uses: pytorch/test-infra/.github/workflows/generate_binary_build_matrix.yml@main
+    with:
+      package-type: wheel
+      os: windows-arm64
+      test-infra-repository: pytorch/test-infra
+      test-infra-ref: main
+      with-cuda: disable
+
+  build:
+    needs: generate-matrix
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - repository: pytorch/vision
+            smoke-test-script: test/smoke_test.py
+            pre-script: packaging/pre_build_script_arm64.sh
+            package-name: torchvision
+            architecture: "arm64"
+    name: ${{ matrix.repository }}
+    uses: pytorch/test-infra/.github/workflows/build_wheels_windows.yml@main
+    with:
+      repository: ${{ matrix.repository }}
+      ref: ""
+      test-infra-repository: pytorch/test-infra
+      test-infra-ref: main
+      pre-script: ${{ matrix.pre-script }}
+      build-matrix: ${{ needs.generate-matrix.outputs.matrix }}
+      package-name: ${{ matrix.package-name }}
+      smoke-test-script: ${{ matrix.smoke-test-script }}
+      trigger-event: ${{ github.event_name }}
+      architecture: ${{ matrix.architecture }}

.github/workflows/prototype-tests-linux-gpu.yml

@@ -21,7 +21,7 @@ jobs:
           - python-version: "3.9"
             runner: linux.g5.4xlarge.nvidia.gpu
             gpu-arch-type: cuda
-            gpu-arch-version: "11.8"
+            gpu-arch-version: "12.6"
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:

.github/workflows/tests.yml

@@ -24,7 +24,7 @@ jobs:
           - python-version: 3.9
             runner: linux.g5.4xlarge.nvidia.gpu
             gpu-arch-type: cuda
-            gpu-arch-version: "11.8"
+            gpu-arch-version: "12.6"
       fail-fast: false
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:

CONTRIBUTING.md

@@ -38,13 +38,13 @@ instructions](https://pytorch.org/get-started/locally/). Note that the official
 instructions may ask you to install torchvision itself. If you are doing development
 on torchvision, you should not install prebuilt torchvision packages.
 
-**Optionally**, install `libpng` and `libjpeg-turbo` if you want to enable
+**Optionally**, install `libpng`, `libjpeg-turbo` and `libwebp` if you want to enable
 support for
-native encoding / decoding of PNG and JPEG formats in
+native encoding / decoding of PNG, JPEG and WebP formats in
 [torchvision.io](https://pytorch.org/vision/stable/io.html#image):
 
 ```bash
-conda install libpng libjpeg-turbo -c pytorch
+conda install libpng libjpeg-turbo libwebp -c pytorch
 ```
 
 Note: you can use the `TORCHVISION_INCLUDE` and `TORCHVISION_LIBRARY`

packaging/pre_build_script_arm64.sh

@@ -6,9 +6,6 @@ echo "Building vision dependencies and wheel started."
 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"

references/detection/coco_utils.py

@@ -123,7 +123,7 @@ def convert_to_coco_api(ds):
     coco_ds = COCO()
     # annotation IDs need to start at 1, not 0, see torchvision issue #1530
     ann_id = 1
-    dataset = {"images": [], "categories": [], "annotations": []}
+    dataset = {"images": [], "categories": [], "annotations": [], "info": {}}
     categories = set()
     for img_idx in range(len(ds)):
         # find better way to get target

setup.py

@@ -111,7 +111,8 @@ def get_dist(pkgname):
     ]
 
     # Excluding 8.3.* because of https://github.com/pytorch/vision/issues/4934
-    pillow_ver = " >= 5.3.0, !=8.3.*"
+    # TODO remove <11.3 bound and address corresponding deprecation warnings
+    pillow_ver = " >= 5.3.0, !=8.3.*, <11.3"
     pillow_req = "pillow-simd" if get_dist("pillow-simd") is not None else "pillow"
     requirements.append(pillow_req + pillow_ver)
 

test/assets/fakedata/draw_rotated_boxes_fill.png

@@ -21,7 +21,7 @@
 from torch.testing._comparison import BooleanPair, NonePair, not_close_error_metas, NumberPair, TensorLikePair
 from torchvision import io, tv_tensors
 from torchvision.transforms._functional_tensor import _max_value as get_max_value
-from torchvision.transforms.v2.functional import clamp_bounding_boxes, to_image, to_pil_image
+from torchvision.transforms.v2.functional import to_image, to_pil_image
 
 
 IN_OSS_CI = any(os.getenv(var) == "true" for var in ["CIRCLECI", "GITHUB_ACTIONS"])
@@ -410,6 +410,7 @@ def make_bounding_boxes(
     canvas_size=DEFAULT_SIZE,
     *,
     format=tv_tensors.BoundingBoxFormat.XYXY,
+    clamping_mode="soft",
     num_boxes=1,
     dtype=None,
     device="cpu",
@@ -423,13 +424,6 @@ def sample_position(values, max_value):
         format = tv_tensors.BoundingBoxFormat[format]
 
     dtype = dtype or torch.float32
-    int_dtype = dtype in (
-        torch.uint8,
-        torch.int8,
-        torch.int16,
-        torch.int32,
-        torch.int64,
-    )
 
     h, w = (torch.randint(1, s, (num_boxes,)) for s in canvas_size)
     y = sample_position(h, canvas_size[0])
@@ -456,31 +450,19 @@ def sample_position(values, max_value):
     elif format is tv_tensors.BoundingBoxFormat.XYXYXYXY:
         r_rad = r * torch.pi / 180.0
         cos, sin = torch.cos(r_rad), torch.sin(r_rad)
-        x1 = torch.round(x) if int_dtype else x
-        y1 = torch.round(y) if int_dtype else y
-        x2 = torch.round(x1 + w * cos) if int_dtype else x1 + w * cos
-        y2 = torch.round(y1 - w * sin) if int_dtype else y1 - w * sin
-        x3 = torch.round(x2 + h * sin) if int_dtype else x2 + h * sin
-        y3 = torch.round(y2 + h * cos) if int_dtype else y2 + h * cos
-        x4 = torch.round(x1 + h * sin) if int_dtype else x1 + h * sin
-        y4 = torch.round(y1 + h * cos) if int_dtype else y1 + h * cos
+        x1 = x
+        y1 = y
+        x2 = x1 + w * cos
+        y2 = y1 - w * sin
+        x3 = x2 + h * sin
+        y3 = y2 + h * cos
+        x4 = x1 + h * sin
+        y4 = y1 + h * cos
         parts = (x1, y1, x2, y2, x3, y3, x4, y4)
     else:
         raise ValueError(f"Format {format} is not supported")
     out_boxes = torch.stack(parts, dim=-1).to(dtype=dtype, device=device)
-    if tv_tensors.is_rotated_bounding_format(format):
-        # The rotated bounding boxes are not guaranteed to be within the canvas by design,
-        # so we apply clamping. We also add a 2 buffer to the canvas size to avoid
-        # numerical issues during the testing
-        buffer = 4
-        out_boxes = clamp_bounding_boxes(
-            out_boxes, format=format, canvas_size=(canvas_size[0] - buffer, canvas_size[1] - buffer)
-        )
-        if format is tv_tensors.BoundingBoxFormat.XYWHR or format is tv_tensors.BoundingBoxFormat.CXCYWHR:
-            out_boxes[:, :2] += buffer // 2
-        elif format is tv_tensors.BoundingBoxFormat.XYXYXYXY:
-            out_boxes[:, :] += buffer // 2
-    return tv_tensors.BoundingBoxes(out_boxes, format=format, canvas_size=canvas_size)
+    return tv_tensors.BoundingBoxes(out_boxes, format=format, canvas_size=canvas_size, clamping_mode=clamping_mode)
 
 
 def make_detection_masks(size=DEFAULT_SIZE, *, num_masks=1, dtype=None, device="cpu"):