facebookresearch / facebookresearch/sam3
Is mask sampling used at training
Open
- Dominant language
- Python
- Stars
- 11.7k
- Forks
- 1.8k
- PR merge metrics
- No merged PRs in 30d
Description
I was wondering if this loss was used at training
https://github.com/facebookresearch/sam3/blob/5eb25fb54b70ec0cb16f949289053be091e16705/sam3/train/loss/mask_sampling.py#L38C5-L38C47
Contributor guide
Research direction
Start with sam3/train/loss/mask_sampling.py at the linked lines and trace where the mask-sampling loss is called during training. Check the training entry points and configuration that reference it, then document whether it is used and under what conditions in the issue discussion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100