Merge branch 'master' into mobilenetv3_quantized

datumbox · web-flow · commit bc27744e5e88 · 2021-02-01T19:03:22.000Z
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -120,6 +120,16 @@ jobs:
             pip install --user --progress-bar off --editable .
             mypy --config-file mypy.ini
 
+  docstring_parameters_sync:
+    docker:
+      - image: circleci/python:3.7
+    steps:
+      - checkout
+      - run:
+          command: |
+            pip install --user pydocstyle
+            pydocstyle
+
   clang_format:
     docker:
       - image: circleci/python:3.7
@@ -130,7 +140,7 @@ jobs:
             curl https://oss-clang-format.s3.us-east-2.amazonaws.com/linux64/clang-format-linux64 -o clang-format
             chmod +x clang-format
             sudo mv clang-format /opt/clang-format
-            ./travis-scripts/run-clang-format/run-clang-format.py -r torchvision/csrc --clang-format-executable /opt/clang-format
+            ./.circleci/unittest/linux/scripts/run-clang-format.py -r torchvision/csrc --clang-format-executable /opt/clang-format
 
   torchhub_test:
     docker:
@@ -1167,6 +1177,7 @@ workflows:
           - build_docs
       - python_lint
       - python_type_check
+      - docstring_parameters_sync
       - clang_format
       - torchhub_test
       - torch_onnx_test
@@ -1283,6 +1294,7 @@ workflows:
       - circleci_consistency
       - python_lint
       - python_type_check
+      - docstring_parameters_sync
       - clang_format
       - torchhub_test
       - torch_onnx_test
diff --git a/.circleci/config.yml.in b/.circleci/config.yml.in
@@ -120,6 +120,16 @@ jobs:
             pip install --user --progress-bar off --editable .
             mypy --config-file mypy.ini
 
+  docstring_parameters_sync:
+    docker:
+      - image: circleci/python:3.7
+    steps:
+      - checkout
+      - run:
+          command: |
+            pip install --user pydocstyle
+            pydocstyle
+
   clang_format:
     docker:
       - image: circleci/python:3.7
@@ -130,7 +140,7 @@ jobs:
             curl https://oss-clang-format.s3.us-east-2.amazonaws.com/linux64/clang-format-linux64 -o clang-format
             chmod +x clang-format
             sudo mv clang-format /opt/clang-format
-            ./travis-scripts/run-clang-format/run-clang-format.py -r torchvision/csrc --clang-format-executable /opt/clang-format
+            ./.circleci/unittest/linux/scripts/run-clang-format.py -r torchvision/csrc --clang-format-executable /opt/clang-format
 
   torchhub_test:
     docker:
@@ -778,6 +788,7 @@ workflows:
       {{ build_workflows(windows_latest_only=True) }}
       - python_lint
       - python_type_check
+      - docstring_parameters_sync
       - clang_format
       - torchhub_test
       - torch_onnx_test
@@ -796,6 +807,7 @@ workflows:
       - circleci_consistency
       - python_lint
       - python_type_check
+      - docstring_parameters_sync
       - clang_format
       - torchhub_test
       - torch_onnx_test
diff --git a/.circleci/unittest/linux/scripts/run-clang-format.py b/.circleci/unittest/linux/scripts/run-clang-format.py
@@ -1,4 +1,27 @@
 #!/usr/bin/env python
+"""
+MIT License
+
+Copyright (c) 2017 Guillaume Papin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+"""
 """A wrapper script around clang-format, suitable for linting multiple files
 and to use for continuous integration.
 
diff --git a/.gitignore b/.gitignore
@@ -25,3 +25,4 @@ gen.yml
 .idea/
 *.orig
 *-checkpoint.ipynb
+*.venv
diff --git a/references/detection/coco_eval.py b/references/detection/coco_eval.py
@@ -239,6 +239,7 @@ def loadRes(self, resFile):
     """
     Load result file and return a result api object.
     Args:
+        self (obj): coco object with ground truth annotations
         resFile (str): file name of result file
     Returns:
     res (obj): result api object
diff --git a/setup.cfg b/setup.cfg
@@ -11,3 +11,6 @@ max-line-length = 120
 max-line-length = 120
 ignore = F401,E402,F403,W503,W504,F821
 exclude = venv
+
+[pydocstyle]
+select = D417 # Missing argument descriptions in the docstring
diff --git a/test/assets/fakedata/draw_boxes_util.png b/test/assets/fakedata/draw_boxes_util.png
diff --git a/test/test_utils.py b/test/test_utils.py
@@ -86,7 +86,7 @@ def test_draw_boxes(self):
                              [10, 15, 30, 35], [23, 35, 93, 95]], dtype=torch.float)
         labels = ["a", "b", "c", "d"]
         colors = ["green", "#FF00FF", (0, 255, 0), "red"]
-        result = utils.draw_bounding_boxes(img, boxes, labels=labels, colors=colors)
+        result = utils.draw_bounding_boxes(img, boxes, labels=labels, colors=colors, fill=True)
 
         path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "assets", "fakedata", "draw_boxes_util.png")
         if not os.path.exists(path):
diff --git a/torchvision/csrc/ops/cuda/nms_kernel.cu b/torchvision/csrc/ops/cuda/nms_kernel.cu
@@ -101,11 +101,7 @@ at::Tensor nms_kernel(
       " and ",
       scores.size(0))
 
-#if defined(WITH_CUDA) || defined(WITH_HIP)
   at::cuda::CUDAGuard device_guard(dets.device());
-#else
-  TORCH_CHECK(false, "Not compiled with GPU support");
-#endif
 
   if (dets.numel() == 0) {
     return at::empty({0}, dets.options().dtype(at::kLong));
diff --git a/torchvision/datasets/semeion.py b/torchvision/datasets/semeion.py
@@ -41,8 +41,6 @@ def __init__(
             raise RuntimeError('Dataset not found or corrupted.' +
                                ' You can use download=True to download it')
 
-        self.data = []
-        self.labels = []
         fp = os.path.join(self.root, self.filename)
         data = np.loadtxt(fp)
         # convert value to 8 bit unsigned integer
diff --git a/torchvision/datasets/stl10.py b/torchvision/datasets/stl10.py
@@ -67,7 +67,7 @@ def __init__(
                 'You can use download=True to download it')
 
         # now load the picked numpy arrays
-        self.labels: np.ndarray
+        self.labels: Optional[np.ndarray]
         if self.split == 'train':
             self.data, self.labels = self.__loadfile(
                 self.train_list[0][0], self.train_list[1][0])
@@ -182,4 +182,6 @@ def __load_folds(self, folds: Optional[int]) -> None:
         with open(path_to_folds, 'r') as f:
             str_idx = f.read().splitlines()[folds]
             list_idx = np.fromstring(str_idx, dtype=np.uint8, sep=' ')
-            self.data, self.labels = self.data[list_idx, :, :, :], self.labels[list_idx]
+            self.data = self.data[list_idx, :, :, :]
+            if self.labels is not None:
+                self.labels = self.labels[list_idx]
diff --git a/torchvision/datasets/usps.py b/torchvision/datasets/usps.py
@@ -57,8 +57,8 @@ def __init__(
         import bz2
         with bz2.open(full_path) as fp:
             raw_data = [line.decode().split() for line in fp.readlines()]
-            imgs = [[x.split(':')[-1] for x in data[1:]] for data in raw_data]
-            imgs = np.asarray(imgs, dtype=np.float32).reshape((-1, 16, 16))
+            tmp_list = [[x.split(':')[-1] for x in data[1:]] for data in raw_data]
+            imgs = np.asarray(tmp_list, dtype=np.float32).reshape((-1, 16, 16))
             imgs = ((cast(np.ndarray, imgs) + 1) / 2 * 255).astype(dtype=np.uint8)
             targets = [int(d[0]) - 1 for d in raw_data]
 
diff --git a/torchvision/datasets/video_utils.py b/torchvision/datasets/video_utils.py
@@ -229,6 +229,7 @@ def compute_clips(self, num_frames, step, frame_rate=None):
         Args:
             num_frames (int): number of frames for the clip
             step (int): distance between two clips
+            frame_rate (int, optional): The frame rate
         """
         self.num_frames = num_frames
         self.step = step
diff --git a/torchvision/models/detection/_utils.py b/torchvision/models/detection/_utils.py
@@ -86,6 +86,7 @@ def encode_boxes(reference_boxes, proposals, weights):
     Args:
         reference_boxes (Tensor): reference boxes
         proposals (Tensor): boxes to be encoded
+        weights (Tensor[4]): the weights for ``(x, y, w, h)``
     """
 
     # perform some unpacking to make it JIT-fusion friendly
diff --git a/torchvision/models/detection/backbone_utils.py b/torchvision/models/detection/backbone_utils.py
@@ -76,11 +76,18 @@ def resnet_fpn_backbone(
     Args:
         backbone_name (string): resnet architecture. Possible values are 'ResNet', 'resnet18', 'resnet34', 'resnet50',
              'resnet101', 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d', 'wide_resnet50_2', 'wide_resnet101_2'
+        pretrained (bool): If True, returns a model with backbone pre-trained on Imagenet
         norm_layer (torchvision.ops): it is recommended to use the default value. For details visit:
             (https://github.com/facebookresearch/maskrcnn-benchmark/issues/267)
-        pretrained (bool): If True, returns a model with backbone pre-trained on Imagenet
         trainable_layers (int): number of trainable (not frozen) resnet layers starting from final block.
             Valid values are between 0 and 5, with 5 meaning all backbone layers are trainable.
+        returned_layers (list of int): The layers of the network to return. Each entry must be in ``[1, 4]``.
+            By default all layers are returned.
+        extra_blocks (ExtraFPNBlock or None): if provided, extra operations will
+            be performed. It is expected to take the fpn features, the original
+            features and the names of the original features as input, and returns
+            a new list of feature maps and their corresponding names. By
+            default a ``LastLevelMaxPool`` is used.
     """
     backbone = resnet.__dict__[backbone_name](
         pretrained=pretrained,
diff --git a/torchvision/models/quantization/googlenet.py b/torchvision/models/quantization/googlenet.py
@@ -29,6 +29,7 @@ def googlenet(pretrained=False, progress=True, quantize=False, **kwargs):
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
         aux_logits (bool): If True, adds two auxiliary branches that can improve training.
             Default: *False* when pretrained is True otherwise *True*
         transform_input (bool): If True, preprocesses the input according to the method with which it
diff --git a/torchvision/models/quantization/inception.py b/torchvision/models/quantization/inception.py
@@ -38,6 +38,7 @@ def inception_v3(pretrained=False, progress=True, quantize=False, **kwargs):
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
         aux_logits (bool): If True, add an auxiliary branch that can improve training.
             Default: *True*
         transform_input (bool): If True, preprocesses the input according to the method with which it
diff --git a/torchvision/models/quantization/resnet.py b/torchvision/models/quantization/resnet.py
@@ -143,6 +143,7 @@ def resnet18(pretrained=False, progress=True, quantize=False, **kwargs):
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     return _resnet('resnet18', QuantizableBasicBlock, [2, 2, 2, 2], pretrained, progress,
                    quantize, **kwargs)
@@ -155,6 +156,7 @@ def resnet50(pretrained=False, progress=True, quantize=False, **kwargs):
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     return _resnet('resnet50', QuantizableBottleneck, [3, 4, 6, 3], pretrained, progress,
                    quantize, **kwargs)
@@ -167,6 +169,7 @@ def resnext101_32x8d(pretrained=False, progress=True, quantize=False, **kwargs):
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     kwargs['groups'] = 32
     kwargs['width_per_group'] = 8
diff --git a/torchvision/models/quantization/shufflenetv2.py b/torchvision/models/quantization/shufflenetv2.py
@@ -107,6 +107,7 @@ def shufflenet_v2_x0_5(pretrained=False, progress=True, quantize=False, **kwargs
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     return _shufflenetv2('shufflenetv2_x0.5', pretrained, progress, quantize,
                          [4, 8, 4], [24, 48, 96, 192, 1024], **kwargs)
@@ -121,6 +122,7 @@ def shufflenet_v2_x1_0(pretrained=False, progress=True, quantize=False, **kwargs
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     return _shufflenetv2('shufflenetv2_x1.0', pretrained, progress, quantize,
                          [4, 8, 4], [24, 116, 232, 464, 1024], **kwargs)
@@ -135,6 +137,7 @@ def shufflenet_v2_x1_5(pretrained=False, progress=True, quantize=False, **kwargs
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     return _shufflenetv2('shufflenetv2_x1.5', pretrained, progress, quantize,
                          [4, 8, 4], [24, 176, 352, 704, 1024], **kwargs)
@@ -149,6 +152,7 @@ def shufflenet_v2_x2_0(pretrained=False, progress=True, quantize=False, **kwargs
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
         progress (bool): If True, displays a progress bar of the download to stderr
+        quantize (bool): If True, return a quantized version of the model
     """
     return _shufflenetv2('shufflenetv2_x2.0', pretrained, progress, quantize,
                          [4, 8, 4], [24, 244, 488, 976, 2048], **kwargs)
diff --git a/torchvision/models/segmentation/segmentation.py b/torchvision/models/segmentation/segmentation.py
@@ -69,6 +69,7 @@ def _segm_model(name, backbone_name, num_classes, aux, pretrained_backbone=True)
 def _load_model(arch_type, backbone, pretrained, progress, num_classes, aux_loss, **kwargs):
     if pretrained:
         aux_loss = True
+        kwargs["pretrained_backbone"] = False
     model = _segm_model(arch_type, backbone, num_classes, aux_loss, **kwargs)
     if pretrained:
         _load_weights(model, arch_type, backbone, progress)
@@ -152,8 +153,8 @@ def deeplabv3_resnet101(pretrained=False, progress=True,
         pretrained (bool): If True, returns a model pre-trained on COCO train2017 which
             contains the same classes as Pascal VOC
         progress (bool): If True, displays a progress bar of the download to stderr
-        num_classes (int): number of output classes of the model (including the background)
-        aux_loss (bool): If True, it uses an auxiliary loss
+        num_classes (int): The number of classes
+        aux_loss (bool): If True, include an auxiliary classifier
     """
     return _load_model('deeplabv3', 'resnet101', pretrained, progress, num_classes, aux_loss, **kwargs)
 
diff --git a/torchvision/utils.py b/torchvision/utils.py
@@ -4,8 +4,7 @@
 import math
 import warnings
 import numpy as np
-from PIL import Image, ImageDraw
-from PIL import ImageFont
+from PIL import Image, ImageDraw, ImageFont, ImageColor
 
 __all__ = ["make_grid", "save_image", "draw_bounding_boxes"]
 
@@ -115,7 +114,6 @@ def norm_range(t, value_range):
 def save_image(
     tensor: Union[torch.Tensor, List[torch.Tensor]],
     fp: Union[Text, pathlib.Path, BinaryIO],
-    normalize: bool = False,
     format: Optional[str] = None,
     **kwargs
 ) -> None:
@@ -143,6 +141,7 @@ def draw_bounding_boxes(
     boxes: torch.Tensor,
     labels: Optional[List[str]] = None,
     colors: Optional[List[Union[str, Tuple[int, int, int]]]] = None,
+    fill: Optional[bool] = False,
     width: int = 1,
     font: Optional[str] = None,
     font_size: int = 10
@@ -151,15 +150,17 @@ def draw_bounding_boxes(
     """
     Draws bounding boxes on given image.
     The values of the input image should be uint8 between 0 and 255.
+    If filled, Resulting Tensor should be saved as PNG image.
 
     Args:
         image (Tensor): Tensor of shape (C x H x W)
-        bboxes (Tensor): Tensor of size (N, 4) containing bounding boxes in (xmin, ymin, xmax, ymax) format. Note that
+        boxes (Tensor): Tensor of size (N, 4) containing bounding boxes in (xmin, ymin, xmax, ymax) format. Note that
             the boxes are absolute coordinates with respect to the image. In other words: `0 <= xmin < xmax < W` and
             `0 <= ymin < ymax < H`.
         labels (List[str]): List containing the labels of bounding boxes.
         colors (List[Union[str, Tuple[int, int, int]]]): List containing the colors of bounding boxes. The colors can
             be represented as `str` or `Tuple[int, int, int]`.
+        fill (bool): If `True` fills the bounding box with specified color.
         width (int): Width of bounding box.
         font (str): A filename containing a TrueType font. If the file is not found in this filename, the loader may
             also search in other directories, such as the `fonts/` directory on Windows or `/Library/Fonts/`,
@@ -179,12 +180,31 @@ def draw_bounding_boxes(
 
     img_boxes = boxes.to(torch.int64).tolist()
 
-    draw = ImageDraw.Draw(img_to_draw)
+    if fill:
+        draw = ImageDraw.Draw(img_to_draw, "RGBA")
+
+    else:
+        draw = ImageDraw.Draw(img_to_draw)
+
     txt_font = ImageFont.load_default() if font is None else ImageFont.truetype(font=font, size=font_size)
 
     for i, bbox in enumerate(img_boxes):
-        color = None if colors is None else colors[i]
-        draw.rectangle(bbox, width=width, outline=color)
+        if colors is None:
+            color = None
+        else:
+            color = colors[i]
+
+        if fill:
+            if color is None:
+                fill_color = (255, 255, 255, 100)
+            elif isinstance(color, str):
+                # This will automatically raise Error if rgb cannot be parsed.
+                fill_color = ImageColor.getrgb(color) + (100,)
+            elif isinstance(color, tuple):
+                fill_color = color + (100,)
+            draw.rectangle(bbox, width=width, outline=color, fill=fill_color)
+        else:
+            draw.rectangle(bbox, width=width, outline=color)
 
         if labels is not None:
             draw.text((bbox[0], bbox[1]), labels[i], fill=color, font=txt_font)
diff --git a/travis-scripts/run-clang-format/LICENSE b/travis-scripts/run-clang-format/LICENSE

-Original file line number
+Diff line change
 .idea/
 *.orig
 *-checkpoint.ipynb
 +*.venv