pytorch / pytorch/vision

VideoClips.get_clip to provide to users some clipId and a way to get meta information about clip pts/time in video

Open
#3,340 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement module: datasets module: video
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

It would be nice for debugging to have VideoClips provide not only video_idx but also clip_idx. With that index one should have a way to get the temporal location corresponding to the sampled clip.

This allows to correlate the sampled clip with subtitles or just scroll into the video for debugging. Currently the returned info object just has video_fps property, clip_idx is not there.

cc @pmeier @bjuncek

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the VideoClips entry point and the code that constructs its returned info object. Trace how video_idx and video_fps are populated, then determine how clip_idx and its temporal location should be exposed; done means callers can correlate a sampled clip with video time or subtitles.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.