Merge branch 'main' of github.com:pytorch/vision into extra_decoders

Author: NicolasHug

.github/workflows/lint.yml

@@ -72,7 +72,7 @@ jobs:
       script: |
         set -euo pipefail
 
-        export PYTHON_VERSION=3.9
+        export PYTHON_VERSION=3.11
         export GPU_ARCH_TYPE=cpu
         export GPU_ARCH_VERSION=''
 
@@ -83,7 +83,7 @@ jobs:
         conda activate ci
 
         echo '::group::Install lint tools'
-        pip install --progress-bar=off mypy
+        pip install --progress-bar=off "mypy==1.13.0"
         echo '::endgroup::'
 
         echo '::group::Lint Python types'

.gitignore

@@ -16,6 +16,7 @@ docs/source/auto_examples/
 docs/source/gen_modules/
 docs/source/generated/
 docs/source/models/generated/
+docs/source/sg_execution_times.rst
 # pytorch-sphinx-theme gets installed here
 docs/src
 
@@ -42,3 +43,5 @@ xcuserdata/
 # direnv
 .direnv
 .envrc
+
+scripts/release_notes/data.json

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

@@ -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

@@ -54,7 +54,7 @@ DecoderInCallback MemoryBuffer::getCallback(
   MemoryBuffer object(buffer, size);
   return
       [object](uint8_t* out, int size, int whence, uint64_t timeoutMs) mutable
-      -> int {
+          -> int {
         if (out) { // see defs.h file
           // read mode
           return object.read(out, size);

torchvision/csrc/io/decoder/memory_buffer.cpp

@@ -361,7 +361,7 @@ TEST(SyncDecoder, TestMemoryBufferNoSeekableWithFullRead) {
   CHECK(decoder.init(
       params,
       [object](uint8_t* out, int size, int whence, uint64_t timeoutMs) mutable
-      -> int {
+          -> int {
         if (out) { // see defs.h file
           // read mode
           return object.read(out, size);
@@ -401,7 +401,7 @@ TEST(SyncDecoder, TestMemoryBufferNoSeekableWithPartialRead) {
   CHECK(!decoder.init(
       params,
       [object](uint8_t* out, int size, int whence, uint64_t timeoutMs) mutable
-      -> int {
+          -> int {
         if (out) { // see defs.h file
           // read mode
           return object.read(out, size);

torchvision/csrc/io/decoder/sync_decoder_test.cpp

@@ -28,8 +28,8 @@ torch::Tensor encode_jpeg(const torch::Tensor& data, int64_t quality) {
   C10_LOG_API_USAGE_ONCE(
       "torchvision.csrc.io.image.cpu.encode_jpeg.encode_jpeg");
   // Define compression structures and error handling
-  struct jpeg_compress_struct cinfo {};
-  struct torch_jpeg_error_mgr jerr {};
+  struct jpeg_compress_struct cinfo{};
+  struct torch_jpeg_error_mgr jerr{};
 
   // Define buffer to write JPEG information to and its size
   JpegSizeType jpegSize = 0;