OpenGVLab / OpenGVLab/InternVideo
The code for InternVideo2 stage1 teachers
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
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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