pytorch/examples

Video classification example

Open

#895 opened on Mar 18, 2021

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (21,634 stars) (9,429 forks)batch import
good first issue

Description

Hi,

As we all know that video representation learning is a hot topic in computer vision community (thanks to recent advances in self-supervised learning), is it time to add a toy example for video classification? This code would be as simple as image classification examples. For example, we can add an example of video classification using I3D on UCF-101/HMDB-51?

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
PythonPyTorchBasic video data handling
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
The issue requests adding a video classification example similar to existing image classification examples in the repository. The example should use I3D on UCF 101 or HMDB 51. Since the issue is from 2021 and has only one comment, review the conversation for any additional details. The maintainers may need to decide on the scope and whether to include data download scripts. Look at the structure of other examples in the repo (e.g., image classification under vision/) to replicate the pattern. The main work involves writing a training script, defining the I3D model, and handling video data loading.