OpenGVLab / OpenGVLab/InternVideo

test_num_segment、test_num_crop

Open
#124 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

ssv2. full_tuning

--test_num_segment 2 \
--test_num_crop 3 \

to

--test_num_segment 4 \
--test_num_crop 3 \

InternVideo/InternVideo2/single_modality/models/internvideo2.py", line 527, in forward
    x = x + pos_embed
RuntimeError: The size of tensor a (3073) must match the size of tensor b (2049) at non-singleton dimension 1


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 full_tuning command with --test_num_segment 4 and --test_num_crop 3, then inspect InternVideo/InternVideo2/single_modality/models/internvideo2.py at line 527. Compare the tensor shapes for the 3073-token input and 2049-token positional embedding. Done means the reported configuration runs without the positional-embedding size error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, 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.