google-deepmind / google-deepmind/kinetics-i3d

extract features

Open
#66 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.8k
Forks
467
PR merge metrics
No merged PRs in 30d

Description

If n_frames represents the frames of a video, How can I extract features of size n_frames*1024 with rgb_videos as the input?

Contributor guide

Open the contributing guide

Research direction

Start by reading the repository's Python model and RGB-video input paths to determine where intermediate features are exposed. The issue does not name a file, test, or entry point; completion would require a documented, working way to obtain features of size n_frames*1024 from RGB videos.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.