Merge branch 'pytorch:main' into replace

Author: sahilg06

.circleci/config.yml

@@ -174,6 +174,26 @@ commands:
       - store_test_results:
           path: test-results
 
+  download_model_weights:
+    parameters:
+      extract_roots:
+        type: string
+        default: "torchvision/models"
+      background:
+        type: boolean
+        default: true
+    steps:
+      - apt_install:
+          args: parallel wget
+          descr: Install download utilitites
+      - run:
+          name: Download model weights
+          background: << parameters.background >>
+          command: |
+            mkdir -p ~/.cache/torch/hub/checkpoints
+            python scripts/collect_model_urls.py << parameters.extract_roots >> \
+                | parallel -j0 'wget --no-verbose -O ~/.cache/torch/hub/checkpoints/`basename {}` {}\?source=ci'
+
 binary_common: &binary_common
   parameters:
     # Edit these defaults to do a release
@@ -340,14 +360,8 @@ jobs:
     resource_class: xlarge
     steps:
       - checkout
-      - run:
-          name: Download model weights
-          background: true
-          command: |
-            sudo apt update -qy && sudo apt install -qy parallel wget
-            mkdir -p ~/.cache/torch/hub/checkpoints
-            python scripts/collect_model_urls.py torchvision/prototype/models \
-                | parallel -j0 'wget --no-verbose -O ~/.cache/torch/hub/checkpoints/`basename {}` {}\?source=ci'
+      - download_model_weights:
+          extract_roots: torchvision/prototype/models
       - install_torchvision
       - install_prototype_dependencies
       - pip_install:
@@ -1011,12 +1025,13 @@ jobs:
   build_docs:
     <<: *binary_common
     docker:
-      - image: "pytorch/manylinux-cuda100"
+      - image: circleci/python:3.7
     resource_class: 2xlarge+
     steps:
       - attach_workspace:
           at: ~/workspace
       - checkout
+      - download_model_weights
       - run:
           name: Setup
           command: .circleci/unittest/linux/scripts/setup_env.sh
@@ -1069,7 +1084,8 @@ jobs:
             # Don't use "checkout" step since it uses ssh, which cannot git push
             # https://circleci.com/docs/2.0/configuration-reference/#checkout
             set -ex
-            tag=${CIRCLE_TAG:1:5}
+            # Change v1.12.1rc1 into 1.12 (only major.minor)
+            tag=$(echo $CIRCLE_TAG | sed -e 's/v*\([0-9]*\.[0-9]*\).*/\1/')
             target=${tag:-main}
             ~/workspace/.circleci/build_docs/commit_docs.sh ~/workspace $target
 

.circleci/config.yml.in

@@ -5,6 +5,5 @@ set -e
 eval "$(./conda/bin/conda shell.bash hook)"
 conda activate ./env
 
-export PYTORCH_TEST_WITH_SLOW='1'
 python -m torch.utils.collect_env
 pytest --junitxml=test-results/junit.xml -v --durations 20

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

@@ -8,6 +8,5 @@ conda activate ./env
 this_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$this_dir/set_cuda_envs.sh"
 
-export PYTORCH_TEST_WITH_SLOW='1'
 python -m torch.utils.collect_env
 pytest --junitxml=test-results/junit.xml -v --durations 20

.circleci/unittest/windows/scripts/run_test.sh

@@ -21,7 +21,9 @@ supported Python versions.
 +--------------------------+--------------------------+---------------------------------+
 | ``torch``                | ``torchvision``          | ``python``                      |
 +==========================+==========================+=================================+
-| ``main`` / ``nightly``   | ``main`` / ``nightly``   | ``>=3.7``, ``<=3.9``            |
+| ``main`` / ``nightly``   | ``main`` / ``nightly``   | ``>=3.7``, ``<=3.10``           |
++--------------------------+--------------------------+---------------------------------+
+| ``1.11.0``               | ``0.12.0``               | ``>=3.7``, ``<=3.10``           |
 +--------------------------+--------------------------+---------------------------------+
 | ``1.10.2``               | ``0.11.3``               | ``>=3.6``, ``<=3.9``            |
 +--------------------------+--------------------------+---------------------------------+

README.rst

@@ -20,6 +20,8 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
+import os
+
 import pytorch_sphinx_theme
 import torchvision
 
@@ -80,11 +82,16 @@
 # built documents.
 #
 # The short X.Y version.
-# TODO: change to [:2] at v1.0
 version = "main (" + torchvision.__version__ + " )"
 # The full version, including alpha/beta/rc tags.
-# TODO: verify this works as expected
 release = "main"
+VERSION = os.environ.get("VERSION", None)
+if VERSION:
+    # Turn 1.11.0aHASH into 1.11 (major.minor only)
+    version = ".".join(version.split(".")[:2])
+    html_title = " ".join((project, version, "documentation"))
+    release = version
+
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/source/conf.py

@@ -22,7 +22,7 @@
 def show(imgs):
     if not isinstance(imgs, list):
         imgs = [imgs]
-    fix, axs = plt.subplots(ncols=len(imgs), squeeze=False)
+    fig, axs = plt.subplots(ncols=len(imgs), squeeze=False)
     for i, img in enumerate(imgs):
         img = img.detach()
         img = F.to_pil_image(img)

gallery/plot_visualization_utils.py

@@ -1,8 +1,8 @@
-pytorch_version = '1.10.0'
+pytorch_version = '1.11.0'
 
 Pod::Spec.new do |s|
     s.name             = 'LibTorchvision'
-    s.version          = '0.11.1'
+    s.version          = '0.12.0'
     s.authors          = 'PyTorch Team'
     s.license          = { :type => 'BSD' }
     s.homepage         = 'https://github.com/pytorch/vision'

ios/LibTorchvision.podspec

@@ -21,8 +21,14 @@ class RandomMixup(torch.nn.Module):
 
     def __init__(self, num_classes: int, p: float = 0.5, alpha: float = 1.0, inplace: bool = False) -> None:
         super().__init__()
-        assert num_classes > 0, "Please provide a valid positive value for the num_classes."
-        assert alpha > 0, "Alpha param can't be zero."
+
+        if num_classes < 1:
+            raise ValueError(
+                f"Please provide a valid positive value for the num_classes. Got num_classes={num_classes}"
+            )
+
+        if alpha <= 0:
+            raise ValueError("Alpha param can't be zero.")
 
         self.num_classes = num_classes
         self.p = p
@@ -99,8 +105,10 @@ class RandomCutmix(torch.nn.Module):
 
     def __init__(self, num_classes: int, p: float = 0.5, alpha: float = 1.0, inplace: bool = False) -> None:
         super().__init__()
-        assert num_classes > 0, "Please provide a valid positive value for the num_classes."
-        assert alpha > 0, "Alpha param can't be zero."
+        if num_classes < 1:
+            raise ValueError("Please provide a valid positive value for the num_classes.")
+        if alpha <= 0:
+            raise ValueError("Alpha param can't be zero.")
 
         self.num_classes = num_classes
         self.p = p

references/classification/transforms.py

@@ -12,7 +12,8 @@
 
 class CocoEvaluator:
     def __init__(self, coco_gt, iou_types):
-        assert isinstance(iou_types, (list, tuple))
+        if not isinstance(iou_types, (list, tuple)):
+            raise TypeError(f"This constructor expects iou_types of type list or tuple, instead  got {type(iou_types)}")
         coco_gt = copy.deepcopy(coco_gt)
         self.coco_gt = coco_gt
 

references/detection/coco_eval.py

@@ -126,7 +126,10 @@ def _has_valid_annotation(anno):
             return True
         return False
 
-    assert isinstance(dataset, torchvision.datasets.CocoDetection)
+    if not isinstance(dataset, torchvision.datasets.CocoDetection):
+        raise TypeError(
+            f"This function expects dataset of type torchvision.datasets.CocoDetection, instead  got {type(dataset)}"
+        )
     ids = []
     for ds_idx, img_id in enumerate(dataset.ids):
         ann_ids = dataset.coco.getAnnIds(imgIds=img_id, iscrowd=None)

references/detection/coco_utils.py

@@ -1,4 +1,4 @@
-from typing import List, Tuple, Dict, Optional
+from typing import List, Tuple, Dict, Optional, Union
 
 import torch
 import torchvision
@@ -326,3 +326,114 @@ def forward(
                 )
 
         return image, target
+
+
+class FixedSizeCrop(nn.Module):
+    def __init__(self, size, fill=0, padding_mode="constant"):
+        super().__init__()
+        size = tuple(T._setup_size(size, error_msg="Please provide only two dimensions (h, w) for size."))
+        self.crop_height = size[0]
+        self.crop_width = size[1]
+        self.fill = fill  # TODO: Fill is currently respected only on PIL. Apply tensor patch.
+        self.padding_mode = padding_mode
+
+    def _pad(self, img, target, padding):
+        # Taken from the functional_tensor.py pad
+        if isinstance(padding, int):
+            pad_left = pad_right = pad_top = pad_bottom = padding
+        elif len(padding) == 1:
+            pad_left = pad_right = pad_top = pad_bottom = padding[0]
+        elif len(padding) == 2:
+            pad_left = pad_right = padding[0]
+            pad_top = pad_bottom = padding[1]
+        else:
+            pad_left = padding[0]
+            pad_top = padding[1]
+            pad_right = padding[2]
+            pad_bottom = padding[3]
+
+        padding = [pad_left, pad_top, pad_right, pad_bottom]
+        img = F.pad(img, padding, self.fill, self.padding_mode)
+        if target is not None:
+            target["boxes"][:, 0::2] += pad_left
+            target["boxes"][:, 1::2] += pad_top
+            if "masks" in target:
+                target["masks"] = F.pad(target["masks"], padding, 0, "constant")
+
+        return img, target
+
+    def _crop(self, img, target, top, left, height, width):
+        img = F.crop(img, top, left, height, width)
+        if target is not None:
+            boxes = target["boxes"]
+            boxes[:, 0::2] -= left
+            boxes[:, 1::2] -= top
+            boxes[:, 0::2].clamp_(min=0, max=width)
+            boxes[:, 1::2].clamp_(min=0, max=height)
+
+            is_valid = (boxes[:, 0] < boxes[:, 2]) & (boxes[:, 1] < boxes[:, 3])
+
+            target["boxes"] = boxes[is_valid]
+            target["labels"] = target["labels"][is_valid]
+            if "masks" in target:
+                target["masks"] = F.crop(target["masks"][is_valid], top, left, height, width)
+
+        return img, target
+
+    def forward(self, img, target=None):
+        _, height, width = F.get_dimensions(img)
+        new_height = min(height, self.crop_height)
+        new_width = min(width, self.crop_width)
+
+        if new_height != height or new_width != width:
+            offset_height = max(height - self.crop_height, 0)
+            offset_width = max(width - self.crop_width, 0)
+
+            r = torch.rand(1)
+            top = int(offset_height * r)
+            left = int(offset_width * r)
+
+            img, target = self._crop(img, target, top, left, new_height, new_width)
+
+        pad_bottom = max(self.crop_height - new_height, 0)
+        pad_right = max(self.crop_width - new_width, 0)
+        if pad_bottom != 0 or pad_right != 0:
+            img, target = self._pad(img, target, [0, 0, pad_right, pad_bottom])
+
+        return img, target
+
+
+class RandomShortestSize(nn.Module):
+    def __init__(
+        self,
+        min_size: Union[List[int], Tuple[int], int],
+        max_size: int,
+        interpolation: InterpolationMode = InterpolationMode.BILINEAR,
+    ):
+        super().__init__()
+        self.min_size = [min_size] if isinstance(min_size, int) else list(min_size)
+        self.max_size = max_size
+        self.interpolation = interpolation
+
+    def forward(
+        self, image: Tensor, target: Optional[Dict[str, Tensor]] = None
+    ) -> Tuple[Tensor, Optional[Dict[str, Tensor]]]:
+        _, orig_height, orig_width = F.get_dimensions(image)
+
+        min_size = self.min_size[torch.randint(len(self.min_size), (1,)).item()]
+        r = min(min_size / min(orig_height, orig_width), self.max_size / max(orig_height, orig_width))
+
+        new_width = int(orig_width * r)
+        new_height = int(orig_height * r)
+
+        image = F.resize(image, [new_height, new_width], interpolation=self.interpolation)
+
+        if target is not None:
+            target["boxes"][:, 0::2] *= new_width / orig_width
+            target["boxes"][:, 1::2] *= new_height / orig_height
+            if "masks" in target:
+                target["masks"] = F.resize(
+                    target["masks"], [new_height, new_width], interpolation=InterpolationMode.NEAREST
+                )
+
+        return image, target