autogluon / autogluon/autogluon
[BUG] Large and huge version of SAM not working?
Open
bug: unconfirmed
module: multimodal
Needs Triage
- Dominant language
- Python
- Stars
- 10.7k
- Forks
- 1.2k
- Avg merge
- 21h 29m
- Merged PRs (30d)
- 57
Description
I ran the `MultiModalPredictor` using SAM with all three checkpoints - base, huge and large - following your [tutorial](https://auto.gluon.ai/stable/tutorials/multimodal/image_segmentation/beginner_semantic_seg.html). Zero-shotting some images produces only decent results for the base checkpoint. For the large and huge checkpoints, I am getting only blank segmentation results when zero-shotting. Is this because these checkpoints are not supported yet or is it an actual bug?
Contributor guide
Assessment
This issue has not been assessed yet.