Merge branch 'main' into main

Author: datumbox

.circleci/config.yml

@@ -848,7 +848,7 @@ jobs:
     executor:
       name: windows-gpu
     environment:
-      CUDA_VERSION: "11.1"
+      CUDA_VERSION: "11.3"
       PYTHON_VERSION: << parameters.python_version >>
     steps:
       - checkout

.circleci/config.yml.in

@@ -32,8 +32,8 @@ def build_workflows(prefix="", filter_branch=None, upload=False, indentation=6,
         for os_type in ["linux", "macos", "win"]:
             python_versions = PYTHON_VERSIONS
             cu_versions_dict = {
-                "linux": ["cpu", "cu102", "cu111", "cu113", "cu115", "rocm4.3.1", "rocm4.5.2"],
-                "win": ["cpu", "cu111", "cu113", "cu115"],
+                "linux": ["cpu", "cu102", "cu113", "cu115", "rocm4.3.1", "rocm4.5.2"],
+                "win": ["cpu", "cu113", "cu115"],
                 "macos": ["cpu"],
             }
             cu_versions = cu_versions_dict[os_type]

.circleci/regenerate.py

@@ -9,10 +9,11 @@ dependencies:
   - libpng
   - jpeg
   - ca-certificates
-  - h5py
+  - hdf5
   - pip:
     - future
     - pillow >=5.3.0, !=8.3.*
     - scipy
     - av
     - dataclasses
+    - h5py

.circleci/unittest/windows/scripts/environment.yml

@@ -28,7 +28,7 @@ else
 fi
 
 printf "Installing PyTorch with %s\n" "${cudatoolkit}"
-conda install -y -c "pytorch-${UPLOAD_CHANNEL}" -c conda-forge "pytorch-${UPLOAD_CHANNEL}"::pytorch[build="*${version}*"] "${cudatoolkit}" pytest
+conda install -y -c "pytorch-${UPLOAD_CHANNEL}" -c nvidia "pytorch-${UPLOAD_CHANNEL}"::pytorch[build="*${version}*"] "${cudatoolkit}" pytest
 
 torch_cuda=$(python -c "import torch; print(torch.cuda.is_available())")
 echo torch.cuda.is_available is $torch_cuda

.circleci/unittest/windows/scripts/install.sh

@@ -47,7 +47,8 @@ Operators
     FeaturePyramidNetwork
     StochasticDepth
     FrozenBatchNorm2d
-    ConvNormActivation
+    Conv2dNormActivation
+    Conv3dNormActivation
     SqueezeExcitation
     DropBlock2d
     DropBlock3d

docs/source/ops.rst

@@ -274,6 +274,7 @@ def init_distributed_mode(args):
     torch.distributed.init_process_group(
         backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
     )
+    torch.distributed.barrier()
     setup_for_distributed(args.rank == 0)
 
 

references/classification/utils.py

@@ -267,6 +267,7 @@ def setup_ddp(args):
         world_size=args.world_size,
         init_method=args.dist_url,
     )
+    torch.distributed.barrier()
 
 
 def reduce_across_processes(val):

references/optical_flow/utils.py

@@ -291,4 +291,5 @@ def init_distributed_mode(args):
     torch.distributed.init_process_group(
         backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
     )
+    torch.distributed.barrier()
     setup_for_distributed(args.rank == 0)

references/segmentation/utils.py

@@ -250,4 +250,5 @@ def init_distributed_mode(args):
     torch.distributed.init_process_group(
         backend=args.dist_backend, init_method=args.dist_url, world_size=args.world_size, rank=args.rank
     )
+    torch.distributed.barrier()
     setup_for_distributed(args.rank == 0)

references/video_classification/utils.py

@@ -1,13 +1,18 @@
 # In[1]:
 
-
+# imports and set configuration
 import pandas as pd
+from retrieve_prs_data import run
 
+exclude_prototype = True
+data_filename = "10.0_to_11.0-rc2.json"
+previous_release = "v10.0"
+current_release = "v11.0-rc2"
 
 # In[2]:
 
 
-df = pd.read_json("10.0_to_11.0-rc2.json").T
+df = pd.read_json(data_filename).T
 df.tail()
 
 
@@ -76,6 +81,8 @@
 def format_prs(mod_df):
     out = []
     for idx, row in mod_df.iterrows():
+        if exclude_prototype and row["prototype"]:
+            continue
         modules = idx
         # Put "documentation" and "tests" first for sorting to be dece
         for last_module in ("documentation", "tests"):
@@ -119,3 +126,13 @@ def format_prs(mod_df):
 # Missing PRs are these ones... classify them manually
 missing_prs = pd.concat([mod_df, included_prs]).drop_duplicates(subset="pr_number", keep=False)
 print(format_prs(missing_prs))
+
+# In[12]:
+
+# Generate list of contributors
+print()
+print("## Contributors")
+
+command_to_run = f"{{ git shortlog -s {previous_release}..{current_release} | cut -f2- & git log -s {previous_release}..{current_release} | grep Co-authored | cut -f2- -d: | cut -f1 -d\\< | sed 's/^ *//;s/ *$//' ; }} | sort --ignore-case | uniq | tr '\\n' ';' | sed 's/;/, /g;s/, $//' | fold -s"
+rc, output, err = run(command_to_run)
+print(output)

scripts/release_notes/classify_prs.py

@@ -1,9 +1,8 @@
 import itertools
 
-import PIL.Image
 import pytest
 import torch
-from test_prototype_transforms_kernels import make_images, make_bounding_boxes, make_one_hot_labels
+from test_prototype_transforms_functional import make_images, make_bounding_boxes, make_one_hot_labels
 from torchvision.prototype import transforms, features
 from torchvision.transforms.functional import to_pil_image
 
@@ -25,15 +24,6 @@ def make_vanilla_tensor_bounding_boxes(*args, **kwargs):
         yield bounding_box.data
 
 
-INPUT_CREATIONS_FNS = {
-    features.Image: make_images,
-    features.BoundingBox: make_bounding_boxes,
-    features.OneHotLabel: make_one_hot_labels,
-    torch.Tensor: make_vanilla_tensor_images,
-    PIL.Image.Image: make_pil_images,
-}
-
-
 def parametrize(transforms_with_inputs):
     return pytest.mark.parametrize(
         ("transform", "input"),
@@ -52,15 +42,21 @@ def parametrize(transforms_with_inputs):
 def parametrize_from_transforms(*transforms):
     transforms_with_inputs = []
     for transform in transforms:
-        dispatcher = transform._DISPATCHER
-        if dispatcher is None:
-            continue
-
-        for type_ in dispatcher._kernels:
+        for creation_fn in [
+            make_images,
+            make_bounding_boxes,
+            make_one_hot_labels,
+            make_vanilla_tensor_images,
+            make_pil_images,
+        ]:
+            inputs = list(creation_fn())
             try:
-                inputs = INPUT_CREATIONS_FNS[type_]()
-            except KeyError:
+                output = transform(inputs[0])
+            except Exception:
                 continue
+            else:
+                if output is inputs[0]:
+                    continue
 
             transforms_with_inputs.append((transform, inputs))
 
@@ -69,7 +65,7 @@ def parametrize_from_transforms(*transforms):
 
 class TestSmoke:
     @parametrize_from_transforms(
-        transforms.RandomErasing(),
+        transforms.RandomErasing(p=1.0),
         transforms.HorizontalFlip(),
         transforms.Resize([16, 16]),
         transforms.CenterCrop([16, 16]),
@@ -141,35 +137,6 @@ def test_auto_augment(self, transform, input):
     def test_normalize(self, transform, input):
         transform(input)
 
-    @parametrize(
-        [
-            (
-                transforms.ConvertColorSpace("grayscale"),
-                itertools.chain(
-                    make_images(),
-                    make_vanilla_tensor_images(color_spaces=["rgb"]),
-                    make_pil_images(color_spaces=["rgb"]),
-                ),
-            )
-        ]
-    )
-    def test_convert_bounding_color_space(self, transform, input):
-        transform(input)
-
-    @parametrize(
-        [
-            (
-                transforms.ConvertBoundingBoxFormat("xyxy", old_format="xywh"),
-                itertools.chain(
-                    make_bounding_boxes(),
-                    make_vanilla_tensor_bounding_boxes(formats=["xywh"]),
-                ),
-            )
-        ]
-    )
-    def test_convert_bounding_box_format(self, transform, input):
-        transform(input)
-
     @parametrize(
         [
             (

test/test_prototype_transforms.py

@@ -3,7 +3,7 @@
 
 import pytest
 import torch.testing
-import torchvision.prototype.transforms.kernels as K
+import torchvision.prototype.transforms.functional as F
 from torch import jit
 from torch.nn.functional import one_hot
 from torchvision.prototype import features
@@ -134,10 +134,10 @@ def __init__(self, *args, **kwargs):
         self.kwargs = kwargs
 
 
-class KernelInfo:
+class FunctionalInfo:
     def __init__(self, name, *, sample_inputs_fn):
         self.name = name
-        self.kernel = getattr(K, name)
+        self.functional = getattr(F, name)
         self._sample_inputs_fn = sample_inputs_fn
 
     def sample_inputs(self):
@@ -146,21 +146,21 @@ def sample_inputs(self):
     def __call__(self, *args, **kwargs):
         if len(args) == 1 and not kwargs and isinstance(args[0], SampleInput):
             sample_input = args[0]
-            return self.kernel(*sample_input.args, **sample_input.kwargs)
+            return self.functional(*sample_input.args, **sample_input.kwargs)
 
-        return self.kernel(*args, **kwargs)
+        return self.functional(*args, **kwargs)
 
 
-KERNEL_INFOS = []
+FUNCTIONAL_INFOS = []
 
 
 def register_kernel_info_from_sample_inputs_fn(sample_inputs_fn):
-    KERNEL_INFOS.append(KernelInfo(sample_inputs_fn.__name__, sample_inputs_fn=sample_inputs_fn))
+    FUNCTIONAL_INFOS.append(FunctionalInfo(sample_inputs_fn.__name__, sample_inputs_fn=sample_inputs_fn))
     return sample_inputs_fn
 
 
 @register_kernel_info_from_sample_inputs_fn
-def horizontal_flip_image():
+def horizontal_flip_image_tensor():
     for image in make_images():
         yield SampleInput(image)
 
@@ -172,12 +172,12 @@ def horizontal_flip_bounding_box():
 
 
 @register_kernel_info_from_sample_inputs_fn
-def resize_image():
+def resize_image_tensor():
     for image, interpolation in itertools.product(
         make_images(),
         [
-            K.InterpolationMode.BILINEAR,
-            K.InterpolationMode.NEAREST,
+            F.InterpolationMode.BILINEAR,
+            F.InterpolationMode.NEAREST,
         ],
     ):
         height, width = image.shape[-2:]
@@ -200,20 +200,20 @@ def resize_bounding_box():
 
 
 class TestKernelsCommon:
-    @pytest.mark.parametrize("kernel_info", KERNEL_INFOS, ids=lambda kernel_info: kernel_info.name)
-    def test_scriptable(self, kernel_info):
-        jit.script(kernel_info.kernel)
+    @pytest.mark.parametrize("functional_info", FUNCTIONAL_INFOS, ids=lambda functional_info: functional_info.name)
+    def test_scriptable(self, functional_info):
+        jit.script(functional_info.functional)
 
     @pytest.mark.parametrize(
-        ("kernel_info", "sample_input"),
+        ("functional_info", "sample_input"),
         [
-            pytest.param(kernel_info, sample_input, id=f"{kernel_info.name}-{idx}")
-            for kernel_info in KERNEL_INFOS
-            for idx, sample_input in enumerate(kernel_info.sample_inputs())
+            pytest.param(functional_info, sample_input, id=f"{functional_info.name}-{idx}")
+            for functional_info in FUNCTIONAL_INFOS
+            for idx, sample_input in enumerate(functional_info.sample_inputs())
         ],
     )
-    def test_eager_vs_scripted(self, kernel_info, sample_input):
-        eager = kernel_info(sample_input)
-        scripted = jit.script(kernel_info.kernel)(*sample_input.args, **sample_input.kwargs)
+    def test_eager_vs_scripted(self, functional_info, sample_input):
+        eager = functional_info(sample_input)
+        scripted = jit.script(functional_info.functional)(*sample_input.args, **sample_input.kwargs)
 
         torch.testing.assert_close(eager, scripted)

test/test_prototype_transforms_kernels.py renamed to test/test_prototype_transforms_functional.py

@@ -1,4 +1,5 @@
 import os
+import sys
 
 import numpy as np
 import pytest
@@ -958,6 +959,17 @@ def test_random_apply(device):
 )
 @pytest.mark.parametrize("channels", [1, 3])
 def test_gaussian_blur(device, channels, meth_kwargs):
+    if all(
+        [
+            device == "cuda",
+            channels == 1,
+            meth_kwargs["kernel_size"] in [23, [23]],
+            torch.version.cuda == "11.3",
+            sys.platform in ("win32", "cygwin"),
+        ]
+    ):
+        pytest.skip("Fails on Windows, see https://github.com/pytorch/vision/issues/5464")
+
     tol = 1.0 + 1e-10
     torch.manual_seed(12)
     _test_class_op(

test/test_transforms_tensor.py

@@ -47,6 +47,27 @@ torch::Tensor decode_jpeg_cuda(
 
   TORCH_CHECK(device.is_cuda(), "Expected a cuda device")
 
+  int major_version;
+  int minor_version;
+  nvjpegStatus_t get_major_property_status =
+      nvjpegGetProperty(MAJOR_VERSION, &major_version);
+  nvjpegStatus_t get_minor_property_status =
+      nvjpegGetProperty(MINOR_VERSION, &minor_version);
+
+  TORCH_CHECK(
+      get_major_property_status == NVJPEG_STATUS_SUCCESS,
+      "nvjpegGetProperty failed: ",
+      get_major_property_status);
+  TORCH_CHECK(
+      get_minor_property_status == NVJPEG_STATUS_SUCCESS,
+      "nvjpegGetProperty failed: ",
+      get_minor_property_status);
+  if ((major_version < 11) || ((major_version == 11) && (minor_version < 6))) {
+    TORCH_WARN_ONCE(
+        "There is a memory leak issue in the nvjpeg library for CUDA versions < 11.6. "
+        "Make sure to rely on CUDA 11.6 or above before using decode_jpeg(..., device='cuda').");
+  }
+
   at::cuda::CUDAGuard device_guard(device);
 
   // Create global nvJPEG handle

torchvision/csrc/io/image/cuda/decode_jpeg_cuda.cpp

@@ -145,6 +145,10 @@ def decode_jpeg(
             with `nvjpeg <https://developer.nvidia.com/nvjpeg>`_. This is only
             supported for CUDA version >= 10.1
 
+            .. warning::
+                There is a memory leak in the nvjpeg library for CUDA versions < 11.6.
+                Make sure to rely on CUDA 11.6 or above before using ``device="cuda"``.
+
     Returns:
         output (Tensor[image_channels, image_height, image_width])
     """