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

Author: NicolasHug

.circleci/config.yml

@@ -76,13 +76,6 @@ def build_workflows(prefix="", filter_branch=None, upload=False, indentation=6,
                         if os_type != "win" and btype == "conda":
                             continue
 
-                        # Not supporting Python 3.11 conda packages at the
-                        # moment since the necessary dependencies are not
-                        # available. Windows 3.11 Wheels will be built from
-                        # CircleCI here, however.
-                        if python_version == "3.11" and btype == "conda":
-                            continue
-
                         w += workflow_pair(
                             btype, os_type, python_version, cu_version, unicode, prefix, upload, filter_branch=fb
                         )

.circleci/regenerate.py

@@ -6,4 +6,17 @@ eval "$(./conda/bin/conda shell.bash hook)"
 conda activate ./env
 
 python -m torch.utils.collect_env
-pytest --junitxml=test-results/junit.xml -v --durations 20
+
+case "$(uname -s)" in
+  Darwin*)
+    # The largest macOS runner is not able to handle the regular test suite plus the transforms v2 tests at the same
+    # time due to insufficient resources. Thus, we ignore the transforms v2 tests at first and run them in a separate
+    # step afterwards.
+    GLOB='test/test_transforms_v2*'
+    pytest --junitxml=test-results/junit.xml -v --durations 20 --ignore-glob="${GLOB}"
+    eval "pytest --junitxml=test-results/junit-transforms-v2.xml -v --durations 20 ${GLOB}"
+    ;;
+  *)
+    pytest --junitxml=test-results/junit.xml -v --durations 20
+    ;;
+esac

.circleci/unittest/linux/scripts/run_test.sh

@@ -39,9 +39,9 @@ jobs:
         fi
 
         # Create Conda Env
-        conda create -yp ci_env python="${PYTHON_VERSION}" numpy libpng jpeg scipy
+        conda create -yp ci_env python="${PYTHON_VERSION}" numpy libpng jpeg scipy 'ffmpeg<4.3'
         conda activate /work/ci_env
-        
+
         # Install PyTorch, Torchvision, and testing libraries
         set -ex
         conda install \

.github/workflows/test-linux-cpu.yml

@@ -43,7 +43,7 @@ jobs:
         fi
 
         # Create Conda Env
-        conda create -yp ci_env python="${PYTHON_VERSION}" numpy libpng jpeg scipy
+        conda create -yp ci_env python="${PYTHON_VERSION}" numpy libpng jpeg scipy 'ffmpeg<4.3'
         conda activate /work/ci_env
 
         # Install PyTorch, Torchvision, and testing libraries

.github/workflows/test-linux-gpu.yml

@@ -33,6 +33,8 @@
 
 sys.path.append(os.path.abspath("."))
 
+torchvision.disable_beta_transforms_warning()
+
 # -- General configuration ------------------------------------------------
 
 # Required version of sphinx is set from docs/requirements.txt

docs/source/conf.py

@@ -14,11 +14,10 @@ transformations.
 This is useful if you have to build a more complex transformation pipeline
 (e.g. in the case of segmentation tasks).
 
-Most transformations accept both `PIL <https://pillow.readthedocs.io>`_
-images and tensor images, although some transformations are :ref:`PIL-only
-<transforms_pil_only>` and some are :ref:`tensor-only
-<transforms_tensor_only>`. The :ref:`conversion_transforms` may be used to
-convert to and from PIL images.
+Most transformations accept both `PIL <https://pillow.readthedocs.io>`_ images
+and tensor images, although some transformations are PIL-only and some are
+tensor-only. The :ref:`conversion_transforms` may be used to convert to and from
+PIL images, or for converting dtypes and ranges.
 
 The transformations that accept tensor images also accept batches of tensor
 images. A Tensor Image is a tensor with ``(C, H, W)`` shape, where ``C`` is a
@@ -70,8 +69,10 @@ The following examples illustrate the use of the available transforms:
     produce the same results.
 
 
-Scriptable transforms
----------------------
+Transforms scriptability
+------------------------
+
+.. TODO: Add note about v2 scriptability (in next PR)
 
 In order to script the transformations, please use ``torch.nn.Sequential`` instead of :class:`Compose`.
 
@@ -89,100 +90,120 @@ Make sure to use only scriptable transformations, i.e. that work with ``torch.Te
 For any custom transformations to be used with ``torch.jit.script``, they should be derived from ``torch.nn.Module``.
 
 
-Compositions of transforms
---------------------------
+Geometry
+--------
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
-    Compose
-
+    Resize
+    v2.Resize
+    RandomCrop
+    v2.RandomCrop
+    RandomResizedCrop
+    v2.RandomResizedCrop
+    CenterCrop
+    v2.CenterCrop
+    FiveCrop
+    v2.FiveCrop
+    TenCrop
+    v2.TenCrop
+    Pad
+    v2.Pad
+    RandomAffine
+    v2.RandomAffine
+    RandomPerspective
+    v2.RandomPerspective
+    RandomRotation
+    v2.RandomRotation
+    RandomHorizontalFlip
+    v2.RandomHorizontalFlip
+    RandomVerticalFlip
+    v2.RandomVerticalFlip
 
-Transforms on PIL Image and torch.\*Tensor
-------------------------------------------
+Color
+-----
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
-    CenterCrop
     ColorJitter
-    FiveCrop
+    v2.ColorJitter
     Grayscale
-    Pad
-    RandomAffine
-    RandomApply
-    RandomCrop
+    v2.Grayscale
     RandomGrayscale
-    RandomHorizontalFlip
-    RandomPerspective
-    RandomResizedCrop
-    RandomRotation
-    RandomVerticalFlip
-    Resize
-    TenCrop
+    v2.RandomGrayscale
     GaussianBlur
+    v2.GaussianBlur
     RandomInvert
+    v2.RandomInvert
     RandomPosterize
+    v2.RandomPosterize
     RandomSolarize
+    v2.RandomSolarize
     RandomAdjustSharpness
+    v2.RandomAdjustSharpness
     RandomAutocontrast
+    v2.RandomAutocontrast
     RandomEqualize
+    v2.RandomEqualize
 
-
-.. _transforms_pil_only:
-
-Transforms on PIL Image only
-----------------------------
+Composition
+-----------
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
+    Compose
+    v2.Compose
+    RandomApply
+    v2.RandomApply
     RandomChoice
+    v2.RandomChoice
     RandomOrder
+    v2.RandomOrder
 
-.. _transforms_tensor_only:
-
-Transforms on torch.\*Tensor only
----------------------------------
+Miscellaneous
+-------------
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
     LinearTransformation
+    v2.LinearTransformation
     Normalize
+    v2.Normalize
     RandomErasing
-    ConvertImageDtype
+    v2.RandomErasing
+    Lambda
+    v2.Lambda
 
 .. _conversion_transforms:
 
-Conversion Transforms
----------------------
+Conversion
+----------
 
 .. autosummary::
     :toctree: generated/
     :template: class.rst
 
     ToPILImage
+    v2.ToPILImage
+    v2.ToImagePIL
     ToTensor
+    v2.ToTensor
     PILToTensor
+    v2.PILToTensor
+    ConvertImageDtype
+    v2.ConvertImageDtype
+    v2.ConvertDtype
 
-
-Generic Transforms
-------------------
-
-.. autosummary::
-    :toctree: generated/
-    :template: class.rst
-
-    Lambda
-
-
-Automatic Augmentation Transforms
----------------------------------
+Auto-Augmentation
+-----------------
 
 `AutoAugment <https://arxiv.org/pdf/1805.09501.pdf>`_ is a common Data Augmentation technique that can improve the accuracy of Image Classification models.
 Though the data augmentation policies are directly linked to their trained dataset, empirical studies show that
@@ -196,9 +217,13 @@ The new transform can be used standalone or mixed-and-matched with existing tran
 
     AutoAugmentPolicy
     AutoAugment
+    v2.AutoAugment
     RandAugment
+    v2.RandAugment
     TrivialAugmentWide
+    v2.TrivialAugmentWide
     AugMix
+    v2.AugMix
 
 .. _functional_transforms:
 

docs/source/transforms.rst

@@ -13,4 +13,8 @@ setup_visual_studio_constraint
 setup_junit_results_folder
 export CUDATOOLKIT_CHANNEL="nvidia"
 
-conda build -c $CUDATOOLKIT_CHANNEL $CONDA_CHANNEL_FLAGS --no-anaconda-upload --python "$PYTHON_VERSION" packaging/torchvision
+if [[ "$PYTHON_VERSION" == "3.11" ]]; then
+  export CONDA_CHANNEL_FLAGS="${CONDA_CHANNEL_FLAGS} -c malfet"
+fi
+
+conda build -c $CUDATOOLKIT_CHANNEL $CONDA_CHANNEL_FLAGS --no-anaconda-upload --no-test --python "$PYTHON_VERSION" packaging/torchvision

packaging/build_conda.sh

@@ -18,7 +18,8 @@
 import numpy as np
 import pytest
 import torch
-from datasets_utils import combinations_grid, create_image_file, create_image_folder, make_tar, make_zip
+from common_utils import combinations_grid
+from datasets_utils import create_image_file, create_image_folder, make_tar, make_zip
 from torch.nn.functional import one_hot
 from torch.testing import make_tensor as _make_tensor
 from torchvision.prototype import datasets