Merge branch 'main' into 313

Author: NicolasHug

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

@@ -23,7 +23,7 @@ jobs:
             gpu-arch-type: cuda
             gpu-arch-version: "11.8"
       fail-fast: false
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     with:
       repository: pytorch/vision
       runner: ${{ matrix.runner }}

.github/workflows/tests.yml

@@ -27,7 +27,7 @@ jobs:
             gpu-arch-type: cuda
             gpu-arch-version: "11.8"
       fail-fast: false
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     with:
       repository: pytorch/vision
       runner: ${{ matrix.runner }}
@@ -107,7 +107,7 @@ jobs:
         ./.github/scripts/unittest.sh
 
   onnx:
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     with:
       repository: pytorch/vision
       test-infra-ref: main
@@ -138,7 +138,7 @@ jobs:
         echo '::endgroup::'
 
   unittests-extended:
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
     if: contains(github.event.pull_request.labels.*.name, 'run-extended')
     with:
       repository: pytorch/vision

packaging/pre_build_script.sh

@@ -32,7 +32,9 @@ else
     conda install -yq ffmpeg=4.2 libjpeg-turbo -c pytorch-nightly
   fi
 
-  yum install -y libjpeg-turbo-devel libwebp-devel freetype gnutls
+  conda install libwebp -yq
+  conda install libjpeg-turbo -c pytorch
+  yum install -y freetype gnutls
   pip install auditwheel
 fi
 

references/depth/stereo/utils/losses.py

@@ -13,7 +13,7 @@ def make_gaussian_kernel(kernel_size: int, sigma: float) -> torch.Tensor:
     y = torch.arange(kernel_size, dtype=torch.float32)
     x = x - (kernel_size - 1) / 2
     y = y - (kernel_size - 1) / 2
-    x, y = torch.meshgrid(x, y)
+    x, y = torch.meshgrid(x, y, indexing="ij")
     grid = (x**2 + y**2) / (2 * sigma**2)
     kernel = torch.exp(-grid)
     kernel = kernel / kernel.sum()

references/video_classification/train.py

@@ -164,7 +164,7 @@ def main(args):
 
     if args.cache_dataset and os.path.exists(cache_path):
         print(f"Loading dataset_train from {cache_path}")
-        dataset, _ = torch.load(cache_path, weights_only=True)
+        dataset, _ = torch.load(cache_path, weights_only=False)
         dataset.transform = transform_train
     else:
         if args.distributed:
@@ -201,7 +201,7 @@ def main(args):
 
     if args.cache_dataset and os.path.exists(cache_path):
         print(f"Loading dataset_test from {cache_path}")
-        dataset_test, _ = torch.load(cache_path, weights_only=True)
+        dataset_test, _ = torch.load(cache_path, weights_only=False)
         dataset_test.transform = transform_test
     else:
         if args.distributed:

test/assets/fakedata/draw_boxes_different_label_colors.png

@@ -1,4 +1,5 @@
 import random
+from copy import deepcopy
 from itertools import chain
 from typing import Mapping, Sequence
 
@@ -322,3 +323,14 @@ def forward(self, x):
         out = model(self.inp)
         # And backward
         out["leaf_module"].float().mean().backward()
+
+    def test_deepcopy(self):
+        # Non-regression test for https://github.com/pytorch/vision/issues/8634
+        model = models.efficientnet_b3(weights=None)
+        extractor = create_feature_extractor(model=model, return_nodes={"classifier.0": "out"})
+
+        extractor.eval()
+        extractor.train()
+        extractor = deepcopy(extractor)
+        extractor.eval()
+        extractor.train()

test/test_backbone_utils.py

@@ -45,6 +45,8 @@
 IS_MACOS = sys.platform == "darwin"
 PILLOW_VERSION = tuple(int(x) for x in PILLOW_VERSION.split("."))
 WEBP_TEST_IMAGES_DIR = os.environ.get("WEBP_TEST_IMAGES_DIR", "")
+# See https://github.com/pytorch/vision/pull/8724#issuecomment-2503964558
+ROCM_WEBP_MESSAGE = "ROCM not built with webp support."
 
 # Hacky way of figuring out whether we compiled with libavif/libheif (those are
 # currenlty disabled by default)

test/test_image.py

@@ -116,6 +116,21 @@ def test_draw_boxes():
     assert_equal(img, img_cp)
 
 
+@pytest.mark.skipif(PILLOW_VERSION < (10, 1), reason="The reference image is only valid for PIL >= 10.1")
+def test_draw_boxes_with_coloured_labels():
+    img = torch.full((3, 100, 100), 255, dtype=torch.uint8)
+    labels = ["a", "b", "c", "d"]
+    colors = ["green", "#FF00FF", (0, 255, 0), "red"]
+    label_colors = ["green", "red", (0, 255, 0), "#FF00FF"]
+    result = utils.draw_bounding_boxes(img, boxes, labels=labels, colors=colors, fill=True, label_colors=label_colors)
+
+    path = os.path.join(
+        os.path.dirname(os.path.abspath(__file__)), "assets", "fakedata", "draw_boxes_different_label_colors.png"
+    )
+    expected = torch.as_tensor(np.array(Image.open(path))).permute(2, 0, 1)
+    assert_equal(result, expected)
+
+
 @pytest.mark.parametrize("fill", [True, False])
 def test_draw_boxes_dtypes(fill):
     img_uint8 = torch.full((3, 100, 100), 255, dtype=torch.uint8)

test/test_utils.py

@@ -3,6 +3,7 @@
 
 #if WEBP_FOUND
 #include "webp/decode.h"
+#include "webp/types.h"
 #endif // WEBP_FOUND
 
 namespace vision {
@@ -44,10 +45,12 @@ torch::Tensor decode_webp(
 
   auto decoded_data =
       decoding_func(encoded_data_p, encoded_data_size, &width, &height);
+
   TORCH_CHECK(decoded_data != nullptr, "WebPDecodeRGB[A] failed.");
 
+  auto deleter = [decoded_data](void*) { WebPFree(decoded_data); };
   auto out = torch::from_blob(
-      decoded_data, {height, width, num_channels}, torch::kUInt8);
+      decoded_data, {height, width, num_channels}, deleter, torch::kUInt8);
 
   return out.permute({2, 0, 1});
 }