pytorchvideo.data.hmdb51¶
-
class
pytorchvideo.data.hmdb51.Hmdb51LabeledVideoPaths(paths_and_labels, path_prefix='')[source]¶ - Pre-processor for Hmbd51 dataset mentioned here -
https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/
- This dataset consists of classwise folds with each class consisting of 3
folds (splits).
- The videos directory is of the format,
video_dir_path/class_x/<somevideo_name>.avi … video_dir_path/class_y/<somevideo_name>.avi
- The splits/fold directory is of the format,
folds_dir_path/class_x_test_split_1.txt folds_dir_path/class_x_test_split_2.txt folds_dir_path/class_x_test_split_3.txt … folds_dir_path/class_y_test_split_1.txt folds_dir_path/class_y_test_split_2.txt folds_dir_path/class_y_test_split_3.txt
- And each text file in the splits directory class_x_test_split_<1 or 2 or 3>.txt
<a video as in video_dir_path/class_x> <0 or 1 or 2> where 0,1,2 corresponds to unused, train split respectively.
- Each video has name of format
<some_name>_<tag1>_<tag2>_<tag_3>_<tag4>_<tag5>_<some_id>.avi
- For more details on tags -
https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/
-
classmethod
from_dir(data_path, split_id=1, split_type='train')[source]¶ Factory function that creates Hmdb51LabeledVideoPaths object form a splits/folds directory.
- Parameters
data_path (str) – The path to the splits/folds directory of HMDB51.
split_id (int) – Fold id to be loaded. Belongs to [1,2,3]
split_type (str) – Split/Fold type to be loaded. It belongs to one of the following, - “train” - “test” - “unused” (This is a small set of videos that are neither of part of test or train fold.)
- Return type
-
classmethod
from_csvs(file_paths, split_type='train')[source]¶ Factory function that creates Hmdb51LabeledVideoPaths object form a list of split files of .txt type
- Parameters
file_paths (List[Union[pathlib.Path, str]]) – The path to the splits/folds directory of HMDB51.
split_type (str) – Split/Fold type to be loaded. - “train” - “test” - “unused”
- Return type
-
pytorchvideo.data.hmdb51.Hmdb51(data_path, clip_sampler, video_sampler=<class 'torch.utils.data.sampler.RandomSampler'>, transform=None, video_path_prefix='', split_id=1, split_type='train', decode_audio=True, decoder='pyav')[source]¶ A helper function to create EncodedVideoDataset object for HMDB51 dataset
- Parameters
data_path (pathlib.Path) – Path to the data. The path type defines how the
should be read (data) –
- 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).
the LabeledVideoPaths class documentation for specific formatting (See) –
and examples. (details) –
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. The clip output is a dictionary with the following format:
- {
‘video’: <video_tensor>, ‘label’: <index_label>, ‘index’: <clip_index>
}
If transform is None, the raw clip output in the above format is returned unmodified.
video_path_prefix (str) – Path to root directory with the videos that are loaded in EncodedVideoDataset. All the video paths before loading are prefixed with this path.
decoder (str) – Defines which backend should be used to decode videos.
split_id (int) –
split_type (str) –
- Return type
