OpenGVLab / OpenGVLab/InternVideo

Segment size for OpenGVLab/InternVL_2_5_HiCo_R16

Open
#246 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

When I want to change the segment size to 130. It gives me an error.
RuntimeError: shape mismatch: value tensor of shape [2048, 4096] cannot be broadcast to indexing result of shape [2080, 4096]

Can I try it with different segment sizes. It also works for 64, 32.

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

Start by reproducing the error in OpenGVLab/InternVL_2_5_HiCo_R16 with segment sizes 130, 64, and 32. Trace how the model handles the segment size and the tensors with shapes [2048, 4096] and [2080, 4096]. Done means determining whether segment size 130 should work and resolving or clearly identifying the shape mismatch.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 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.