facebookresearch / facebookresearch/segment-anything
ISSUE DURING TRAINING SAM MODEL FOR COD TASK
Open
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
Can it happen that the presence of no mask images in the COD-10K dataset can cause issues during loss computation and metric evaluation. As I am facing some issues with it. Sometimes after training the value of my average loss is -2.492 when i am using nn.BCEWithLogits as loss function. And also after training during the evaluation its not predicting any mask
Contributor guide
Research direction
The issue names no files, tests, or reproducible training entry point. Begin by checking whether COD-10K contains empty masks and verifying the BCEWithLogits loss inputs and evaluation predictions; done requires a reproducible diagnosis and a documented corrective change.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100