Skip to content

Releases: RaivoKoot/Video-Dataset-Loading-Pytorch

v2.2

31 Dec 15:19
d0903e0
Compare
Choose a tag to compare

A refactored version, with cleaner and more understandable internal code.

Stable

18 Dec 12:08
868480d
Compare
Choose a tag to compare

Fixed previous bug.
Added support for multiple integer labels per clip.

Buggy Release

09 Dec 19:21
dcbd456
Compare
Choose a tag to compare

Breaking change from 1.0, where in annotations.txt you now need to supply START_FRAME and END_FRAME per sample instead of just NUM_FRAMES. This allows you to use small clips from a whole video if needed.

BUG:
Didn't load enough frames when FRAMES_PER_SEGMENT > 1

Stable

13 Nov 11:01
4c9b533
Compare
Choose a tag to compare

Load videos into PyTorch
Features:

  • A frame sampling strategy that helps with training (Sparse Temporal Sampling - "Temporal Segment Networks")
  • A very fast video loading pipeline that eliminates input bottlenecks
  • Generic and therefore usable with custom datasets with minimum effort
  • Easy out-of-the-box support for torchvision 0.8.0's video-level augmentations/transforms (identical image transforms on an image batch)

Extensive documentation at https://video-dataset-loading-pytorch.readthedocs.io/