OpenGVLab / OpenGVLab/InternVideo

The code for InternVideo2 stage1 teachers

Open
#277 0 comments 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, InternVideo2 is a great work, and I appreciate your contribution to the community. However, I can't find relevant code for using the 2 teachers in stage 1.
As said in the paper:

Specifically, we adopt InternVL-6B [Chen et al., 2023c] and VideoMAEv2-g [Wang et al., 2023b] to transfer unmasked
knowledge via simple projection layers.

However, I don't find the code for the 2 teachers. I read InternVideo2/single_modality/run_distill.py and found the default setting is internvl_clip_6b.

parser.add_argument('--clip_teacher', default='internvl_clip_6b', type=str, help='Name of CLIP teacher')

Can you explain where's the code for simutaneously using 2 teachers?

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

Read InternVideo2/single_modality/run_distill.py, beginning with the --clip_teacher argument and its internvl_clip_6b default; then trace the stage-1 distillation configuration for teacher selection. Done means identifying and documenting whether and where both teachers are used, or confirming that the implementation is absent.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.