OpenGVLab / OpenGVLab/InternVideo

why InternVid-200M performance is not as good as ViClip-InternVid-10M-FLT.pth

Open
#73 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.4k
Forks
160
PR merge metrics
No merged PRs in 30d

Description

hi, since 200M pretrained dataset is much bigger than 10M version, so why the zero shot performance is not superior than 10M?

Contributor guide

No contributing guide indexed for this repository

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

No source file, test, or evaluation entry point is named. Start by locating the zero-shot evaluation for InternVid-200M and ViClip-InternVid-10M-FLT.pth, then compare their evaluation setups and results. Done means providing an evidence-backed explanation for the performance gap.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
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.