OpenGVLab / OpenGVLab/InternVideo
video retrieval problem
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 160
- PR merge metrics
- No merged PRs in 30d
Description
为什么我用 https://huggingface.co/OpenGVLab/InternVideo2-Stage2_6B 中6B的模型提取视频特征进行搜索 (检索代码参考：https://huggingface.co/OpenGVLab/InternVideo2-Stage2_6B/blob/main/demo.py) 还没有 https://huggingface.co/OpenGVLab/InternVideo2-Stage2_1B-224p-f4 中的1B的模型的效果好（检索代码参考：https://github.com/OpenGVLab/InternVideo/blob/main/InternVideo2/multi_modality/demo_video_text_retrieval.ipynb）？求解答
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
Start by comparing the referenced Hugging Face demo.py with InternVideo2/multi_modality/demo_video_text_retrieval.ipynb, including the model and retrieval setup used for each checkpoint. Reproduce the reported comparison and document the configuration or processing difference that explains the 6B model's lower retrieval result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- machine-learning, search
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100