facebookresearch / facebookresearch/co-tracker
How to train with pseudo-labelling?
Open
- Dominant language
- Jupyter Notebook
- Stars
- 5.1k
- Forks
- 389
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I am following your work to launch training with pseudo-labelling using my own dataset of real videos, but I'm having trouble with it.
Could you please provide more details or provide a step-by-step guide on how to fine-tuning with pseudo labels?
Contributor guide
Research direction
The issue names no files, tests, or training entry points. First locate the repository's existing training and fine-tuning guidance, then determine what steps are needed for pseudo-label training on real videos; done means a newcomer can follow a complete step-by-step guide with their own dataset.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100