Expose docs for io and ops package (#1189)

* Expose docs for io and ops package

Had do modify the docstrings to use Napoleon NumPy style, because Napoleon Google Style doesn't support multiple return arguments

* Add video section

docs/source/index.rst

@@ -9,7 +9,9 @@ architectures, and common image transformations for computer vision.
    :caption: Package Reference
 
    datasets
+   io
    models
+   ops
    transforms
    utils
 

docs/source/io.rst

+torchvision.io
+==============
+
+.. currentmodule:: torchvision.io
+
+The :mod:`torchvision.io` package provides functions for performing IO
+operations. They are currently specific to reading and writing video.
+
+Video
+-----
+
+.. autofunction:: read_video
+
+.. autofunction:: read_video_timestamps
+
+.. autofunction:: write_video

docs/source/ops.rst

+torchvision.ops
+===============
+
+.. currentmodule:: torchvision.ops
+
+:mod:`torchvision.ops` implements operators that are specific for Computer Vision.
+
+.. note::
+  Those operators currently do not support TorchScript.
+
+
+.. autofunction:: nms
+.. autofunction:: roi_align
+.. autofunction:: roi_pool
+
+.. autoclass:: RoIAlign
+.. autoclass:: RoIPool

torchvision/io/video.py

@@ -28,11 +28,14 @@ def write_video(filename, video_array, fps, video_codec='libx264', options=None)
     """
     Writes a 4d tensor in [T, H, W, C] format in a video file
 
-    Arguments:
-        filename (str): path where the video will be saved
-        video_array (Tensor[T, H, W, C]): tensor containing the individual frames,
-            as a uint8 tensor in [T, H, W, C] format
-        fps (Number): frames per second
+    Parameters
+    ----------
+    filename : str
+        path where the video will be saved
+    video_array : Tensor[T, H, W, C]
+        tensor containing the individual frames, as a uint8 tensor in [T, H, W, C] format
+    fps : Number
+        frames per second
     """
     _check_av_available()
     video_array = torch.as_tensor(video_array, dtype=torch.uint8).numpy()
@@ -135,18 +138,25 @@ def read_video(filename, start_pts=0, end_pts=None):
     Reads a video from a file, returning both the video frames as well as
     the audio frames
 
-    Arguments:
-        filename (str): path to the video file
-        start_pts (int, optional): the start presentation time of the video
-        end_pts (int, optional): the end presentation time
-
-    Returns:
-        vframes (Tensor[T, H, W, C]): the `T` video frames
-        aframes (Tensor[K, L]): the audio frames, where `K` is the number of channels
-            and `L` is the number of points
-        info (Dict): metadata for the video and audio. Can contain the fields
-            - video_fps (float)
-            - audio_fps (int)
+    Parameters
+    ----------
+    filename : str
+        path to the video file
+    start_pts : int, optional
+        the start presentation time of the video
+    end_pts : int, optional
+        the end presentation time
+
+    Returns
+    -------
+    vframes : Tensor[T, H, W, C]
+        the `T` video frames
+    aframes : Tensor[K, L]
+        the audio frames, where `K` is the number of channels and `L` is the
+        number of points
+    info : Dict
+        metadata for the video and audio. Can contain the fields video_fps (float)
+        and audio_fps (int)
     """
     _check_av_available()
 
@@ -201,13 +211,18 @@ def read_video_timestamps(filename):
 
     Note that the function decodes the whole video frame-by-frame.
 
-    Arguments:
-        filename (str): path to the video file
+    Parameters
+    ----------
+    filename : str
+        path to the video file
+
+    Returns
+    -------
+    pts : List[int]
+        presentation timestamps for each one of the frames in the video.
+    video_fps : int
+        the frame rate for the video
 
-    Returns:
-        pts (List[int]): presentation timestamps for each one of the frames
-            in the video.
-        video_fps (int): the frame rate for the video
     """
     _check_av_available()
     container = av.open(filename, metadata_errors='ignore')

torchvision/ops/boxes.py

@@ -11,17 +11,23 @@ def nms(boxes, scores, iou_threshold):
     IoU greater than iou_threshold with another (higher scoring)
     box.
 
-    Arguments:
-        boxes (Tensor[N, 4]): boxes to perform NMS on. They
-            are expected to be in (x1, y1, x2, y2) format
-        scores (Tensor[N]): scores for each one of the boxes
-        iou_threshold (float): discards all overlapping
-            boxes with IoU < iou_threshold
-
-    Returns:
-        keep (Tensor): int64 tensor with the indices
-            of the elements that have been kept
-            by NMS, sorted in decreasing order of scores
+    Parameters
+    ----------
+    boxes : Tensor[N, 4])
+        boxes to perform NMS on. They
+        are expected to be in (x1, y1, x2, y2) format
+    scores : Tensor[N]
+        scores for each one of the boxes
+    iou_threshold : float
+        discards all overlapping
+        boxes with IoU < iou_threshold
+
+    Returns
+    -------
+    keep : Tensor
+        int64 tensor with the indices
+        of the elements that have been kept
+        by NMS, sorted in decreasing order of scores
     """
     _C = _lazy_import()
     return _C.nms(boxes, scores, iou_threshold)
@@ -34,19 +40,25 @@ def batched_nms(boxes, scores, idxs, iou_threshold):
     Each index value correspond to a category, and NMS
     will not be applied between elements of different categories.
 
-    Arguments:
-        boxes (Tensor[N, 4]): boxes where NMS will be performed. They
-            are expected to be in (x1, y1, x2, y2) format
-        scores (Tensor[N]): scores for each one of the boxes
-        idxs (Tensor[N]): indices of the categories for each
-            one of the boxes.
-        iou_threshold (float): discards all overlapping boxes
-            with IoU < iou_threshold
-
-    Returns:
-        keep (Tensor): int64 tensor with the indices of
-            the elements that have been kept by NMS, sorted
-            in decreasing order of scores
+    Parameters
+    ----------
+    boxes : Tensor[N, 4]
+        boxes where NMS will be performed. They
+        are expected to be in (x1, y1, x2, y2) format
+    scores : Tensor[N]
+        scores for each one of the boxes
+    idxs : Tensor[N]
+        indices of the categories for each one of the boxes.
+    iou_threshold : float
+        discards all overlapping boxes
+        with IoU < iou_threshold
+
+    Returns
+    -------
+    keep : Tensor
+        int64 tensor with the indices of
+        the elements that have been kept by NMS, sorted
+        in decreasing order of scores
     """
     if boxes.numel() == 0:
         return torch.empty((0,), dtype=torch.int64, device=boxes.device)