google-deepmind / google-deepmind/kinetics-i3d

Does the video need to be cropped?

Open
#119 11 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.8k
Forks
467
PR merge metrics
No merged PRs in 30d

Description

Can the model handle not square input of the video? Or does it need to be 224x224?

I plan to fine-tune it on another dataset so will be removing the top layer.

Contributor guide

Open the contributing guide

Research direction

The issue names no files, tests, or entry points. Start by checking the model's expected video dimensions and how removing the top layer affects input handling; done would mean a clear answer about non-square and 224x224 video inputs for fine-tuning.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.