Source code for pytorchvideo.data.ucf101

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

from typing import Any, Callable, Dict, Optional, Type

import torch
from pytorchvideo.data.clip_sampling import ClipSampler

from .labeled_video_dataset import LabeledVideoDataset, labeled_video_dataset


"""
    Action recognition video dataset for UCF101
    <https://www.crcv.ucf.edu/data/UCF101.php>
"""


def Ucf101(
    data_path: str,
    clip_sampler: ClipSampler,
    video_sampler: Type[torch.utils.data.Sampler] = torch.utils.data.RandomSampler,
    transform: Optional[Callable[[Dict[str, Any]], Dict[str, Any]]] = None,
    video_path_prefix: str = "",
    decode_audio: bool = True,
    decoder: str = "pyav",
) -> LabeledVideoDataset:
    """
    A helper function to create ``LabeledVideoDataset`` object for the Ucf101 dataset.

    Args:
        data_path (str): Path to the data. The path type defines how the data
            should be read:

            * For a file path, the file is read and each line is parsed into a
              video path and label.
            * For a directory, the directory structure defines the classes
              (i.e. each subdirectory is a class).

        clip_sampler (ClipSampler): Defines how clips should be sampled from each
                video. See the clip sampling documentation for more information.

        video_sampler (Type[torch.utils.data.Sampler]): Sampler for the internal
                video container. This defines the order videos are decoded and,
                if necessary, the distributed split.

        transform (Callable): This callable is evaluated on the clip output before
                the clip is returned. It can be used for user defined preprocessing and
                augmentations to the clips. See the ``LabeledVideoDataset`` class for clip
                output format.

        video_path_prefix (str): Path to root directory with the videos that are
                loaded in ``LabeledVideoDataset``. All the video paths before loading
                are prefixed with this path.

        decode_audio (bool): If True, also decode audio from video.

        decoder (str): Defines what type of decoder used to decode a video.

    """

    torch._C._log_api_usage_once("PYTORCHVIDEO.dataset.Ucf101")

    return labeled_video_dataset(
        data_path,
        clip_sampler,
        video_sampler,
        transform,
        video_path_prefix,
        decode_audio,
        decoder,
    )