- class torchvision.datasets.UCF101(root: str, annotation_path: str, frames_per_clip: int, step_between_clips: int = 1, frame_rate: Optional[int] = None, fold: int = 1, train: bool = True, transform: Optional[Callable] = None, _precomputed_metadata: Optional[Dict[str, Any]] = None, num_workers: int = 1, _video_width: int = 0, _video_height: int = 0, _video_min_dimension: int = 0, _audio_samples: int = 0, output_format: str = 'THWC')¶
UCF101 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. The dataset itself can be downloaded from the dataset website; annotations that
annotation_pathshould be pointing to can be downloaded from here.
To give an example, for 2 videos with 10 and 15 frames respectively, if
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_clipelements, so not all frames in a video might be present.
Internally, it uses a VideoClips object to handle clip creation.
root (string) – Root directory of the UCF101 Dataset.
annotation_path (str) – path to the folder containing the split files; see docstring above for download instructions of these files
frames_per_clip (int) – number of frames in a clip.
step_between_clips (int, optional) – number of frames between each clip.
fold (int, optional) – which fold to use. Should be between 1 and 3.
train (bool, optional) – if
True, creates a dataset from the train split, otherwise from the
transform (callable, optional) – A function/transform that takes in a TxHxWxC video and returns a transformed version.
output_format (str, optional) – The format of the output video tensors (before transforms). Can be either “THWC” (default) or “TCHW”.
A 3-tuple with the following entries:
video (Tensor[T, H, W, C] or Tensor[T, C, H, W]): 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
- Return type: