Source code for torchvision.datasets.kinetics

from .video_utils import VideoClips
from .utils import list_dir
from .folder import make_dataset
from .vision import VisionDataset


class Kinetics400(VisionDataset):
    """
    `Kinetics-400 <https://deepmind.com/research/open-source/open-source-datasets/kinetics/>`_
    dataset.

    Kinetics-400 is an action recognition video dataset.
    This dataset consider every video as a collection of video clips of fixed size, specified
    by ``frames_per_clip``, where the step in frames between each clip is given by
    ``step_between_clips``.

    To give an example, for 2 videos with 10 and 15 frames respectively, if ``frames_per_clip=5``
    and ``step_between_clips=5``, the dataset size will be (2 + 3) = 5, where the first two
    elements will come from video 1, and the next three elements from video 2.
    Note that we drop clips which do not have exactly ``frames_per_clip`` elements, so not all
    frames in a video might be present.

    Internally, it uses a VideoClips object to handle clip creation.

    Args:
        root (string): Root directory of the Kinetics-400 Dataset.
        frames_per_clip (int): number of frames in a clip
        step_between_clips (int): number of frames between each clip
        transform (callable, optional): A function/transform that  takes in a TxHxWxC video
            and returns a transformed version.

    Returns:
        video (Tensor[T, H, W, C]): the `T` video frames
        audio(Tensor[K, L]): the audio frames, where `K` is the number of channels
            and `L` is the number of points
        label (int): class of the video clip
    """

    def __init__(self, root, frames_per_clip, step_between_clips=1, transform=None):
        super(Kinetics400, self).__init__(root)
        extensions = ('avi',)

        classes = list(sorted(list_dir(root)))
        class_to_idx = {classes[i]: i for i in range(len(classes))}
        self.samples = make_dataset(self.root, class_to_idx, extensions, is_valid_file=None)
        self.classes = classes
        video_list = [x[0] for x in self.samples]
        self.video_clips = VideoClips(video_list, frames_per_clip, step_between_clips)
        self.transform = transform

    def __len__(self):
        return self.video_clips.num_clips()

    def __getitem__(self, idx):
        video, audio, info, video_idx = self.video_clips.get_clip(idx)
        label = self.samples[video_idx][1]

        if self.transform is not None:
            video = self.transform(video)

        return video, audio, label