pytorch / pytorch/vision

The temporal size of MVIT_V2_S can not be greater than 16

Open
#7,345 2 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

📚 The doc issue

In the documentation for the MVIT_V2_S model, the min_temporal_size is given as 16. However, despite my attempts, I have been unable to perform classification on videos with more than 16 frames. It seems that the documentation may be incorrect and that the temporal size of the MVIT_V2_S model is limited to 16 frames.
Is the documentation not correct and it should state that the temporal size has to be 16 or is there anything I'm overlooking and it is possible to chance the temporal size?
(https://pytorch.org/vision/stable/models/generated/torchvision.models.video.mvit_v2_s.html#torchvision.models.video.MViT_V2_S_Weights)

Suggest a potential alternative/fix

No response

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 with the linked MVIT_V2_S_Weights documentation and the MViT_V2_S model entry point in torchvision. Reproduce or verify the reported behavior for videos exceeding 16 frames, then compare it with the documented min_temporal_size. Done means the documentation accurately states the supported temporal size or explains how larger inputs are handled.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, documentation, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.