Merge branch 'master' into add-modulation-for-deformable-convolution

Author: Licht-T

README.rst

@@ -123,6 +123,11 @@ so make sure that it is also available to cmake via the ``CMAKE_PREFIX_PATH``.
 
 For an example setup, take a look at ``examples/cpp/hello_world``.
 
+TorchVision Operators
+---------------------
+In order to get the torchvision operators registered with torch (eg. for the JIT), all you need to do is to ensure that you
+:code:`#include <torchvision/vision.h>` in your project.
+
 Documentation
 =============
 You can find the API documentation on the pytorch website: https://pytorch.org/docs/stable/torchvision/index.html

cmake/TorchVisionConfig.cmake.in

@@ -32,7 +32,7 @@ if(NOT TARGET Python3::Python)
 find_package(Python3 COMPONENTS Development)
 endif()
 
-set_target_properties(TorchVision::TorchVision PROPERTIES INTERFACE_INCLUDE_DIRECTORIES "${PACKAGE_PREFIX_DIR}/@CMAKE_INSTALL_INCLUDEDIR@" INTERFACE_LINK_LIBRARIES "torch;Python3::Python" )
+set_target_properties(TorchVision::TorchVision PROPERTIES INTERFACE_INCLUDE_DIRECTORIES "${${PN}_INCLUDE_DIR}" INTERFACE_LINK_LIBRARIES "torch;Python3::Python" )
 
 
 if(@WITH_CUDA@)

docs/source/io.rst

@@ -24,11 +24,11 @@ In addition to the :mod:`read_video` function, we provide a high-performance
 lower-level API for more fine-grained control compared to the :mod:`read_video` function.
 It does all this whilst fully supporting torchscript.
 
-.. autoclass:: Video
-    :members: next, get_metadata, set_current_stream, seek
+.. autoclass:: VideoReader
+    :members: __next__, get_metadata, set_current_stream, seek
 
 
-Example of usage:
+Example of inspecting a video:
 
 .. code:: python
 
@@ -37,7 +37,7 @@ Example of usage:
     # Constructor allocates memory and a threaded decoder
     # instance per video. At the momet it takes two arguments:
     # path to the video file, and a wanted stream.
-    reader = torchvision.io.Video(video_path, "video")
+    reader = torchvision.io.VideoReader(video_path, "video")
 
     # The information about the video can be retrieved using the 
     # `get_metadata()` method. It returns a dictionary for every stream, with
@@ -50,6 +50,11 @@ Example of usage:
     # following would print out the list of frame rates for every present video stream
     print(reader_md["video"]["fps"])
 
+    # we explicitly select the stream we would like to operate on. In
+    # the constructor we select a default video stream, but
+    # in practice, we can set whichever stream we would like 
+    video.set_current_stream("video:0")
+
 
 Image
 -----

docs/source/models.rst

@@ -350,6 +350,7 @@ the instances set of COCO train2017 and evaluated on COCO val2017.
 Network                           box AP   mask AP   keypoint AP
 ================================  =======  ========  ===========
 Faster R-CNN ResNet-50 FPN        37.0     -         -
+RetinaNet ResNet-50 FPN           36.4     -         -
 Mask R-CNN ResNet-50 FPN          37.9     34.6      -
 ================================  =======  ========  ===========
 
@@ -405,6 +406,7 @@ precision-recall.
 Network                         train time (s / it)  test time (s / it)  memory (GB)
 ==============================  ===================  ==================  ===========
 Faster R-CNN ResNet-50 FPN      0.2288               0.0590              5.2
+RetinaNet ResNet-50 FPN         0.2514               0.0939              4.1
 Mask R-CNN ResNet-50 FPN        0.2728               0.0903              5.4
 Keypoint R-CNN ResNet-50 FPN    0.3789               0.1242              6.8
 ==============================  ===================  ==================  ===========
@@ -416,6 +418,12 @@ Faster R-CNN
 .. autofunction:: torchvision.models.detection.fasterrcnn_resnet50_fpn
 
 
+RetinaNet
+------------
+
+.. autofunction:: torchvision.models.detection.retinanet_resnet50_fpn
+
+
 Mask R-CNN
 ----------
 

docs/source/transforms.rst

@@ -57,77 +57,103 @@ Compositions of transforms
 
 .. autoclass:: Compose
 
-Transforms on PIL Image
------------------------
+Transforms on PIL Image and torch.\*Tensor
+------------------------------------------
 
 .. autoclass:: CenterCrop
+    :members:
 
 .. autoclass:: ColorJitter
+    :members:
 
 .. autoclass:: FiveCrop
+    :members:
 
 .. autoclass:: Grayscale
+    :members:
 
 .. autoclass:: Pad
+    :members:
 
 .. autoclass:: RandomAffine
+    :members:
 
 .. autoclass:: RandomApply
 
-.. autoclass:: RandomChoice
-
 .. autoclass:: RandomCrop
+    :members:
 
 .. autoclass:: RandomGrayscale
+    :members:
 
 .. autoclass:: RandomHorizontalFlip
-
-.. autoclass:: RandomOrder
+    :members:
 
 .. autoclass:: RandomPerspective
+    :members:
 
 .. autoclass:: RandomResizedCrop
+    :members:
 
 .. autoclass:: RandomRotation
+    :members:
 
 .. autoclass:: RandomSizedCrop
+    :members:
 
 .. autoclass:: RandomVerticalFlip
+    :members:
 
 .. autoclass:: Resize
+    :members:
 
 .. autoclass:: Scale
+    :members:
 
 .. autoclass:: TenCrop
+    :members:
 
 .. autoclass:: GaussianBlur
+    :members:
 
-Transforms on torch.\*Tensor
+Transforms on PIL Image only
 ----------------------------
 
+.. autoclass:: RandomChoice
+
+.. autoclass:: RandomOrder
+
+
+Transforms on torch.\*Tensor only
+---------------------------------
+
 .. autoclass:: LinearTransformation
+    :members:
 
 .. autoclass:: Normalize
-	:members: __call__
-	:special-members:
+    :members:
 
 .. autoclass:: RandomErasing
+    :members:
+
+.. autoclass:: ConvertImageDtype
+
 
 Conversion Transforms
 ---------------------
 
 .. autoclass:: ToPILImage
-	:members: __call__
-	:special-members:
+    :members:
 
 .. autoclass:: ToTensor
-	:members: __call__
-	:special-members:
+    :members:
+
 
 Generic Transforms
 ------------------
 
 .. autoclass:: Lambda
+    :members:
 
 
 Functional Transforms