OpenGVLab / OpenGVLab/Ask-Anything

Bugs during training stage2

Open
#71 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.4k
Forks
268
PR merge metrics
No merged PRs in 30d

Description

Hi,
I am trying to run stage2 (video finetuneing) but am running into some issues, specifically with the video_datasets.

Some issues include not defining self.random_shuffle, self.individual :
https://github.com/OpenGVLab/Ask-Anything/blob/6e621d11f7714aa90d047decf6f037bd860598d8/video_chat/dataset/it_dataset.py#L51-L52

or add_second_msg :
https://github.com/OpenGVLab/Ask-Anything/blob/6e621d11f7714aa90d047decf6f037bd860598d8/video_chat/dataset/it_dataset.py#L111

Before they are used, causing some defining issues. Are these variables used in any way? should I just comment them out?
Best,
Orr

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 with video_chat/dataset/it_dataset.py at the referenced lines, then trace how stage2 video fine-tuning loads and uses this dataset. Confirm whether random_shuffle, individual, and add_second_msg are required, and verify that stage2 can run without the reported attribute errors.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.