autogluon / autogluon/autogluon

[BUG] Large and huge version of SAM not working?

Open
#3,990 0 comments 0 reactions 1 assignee Claimed by @Harry-zzh View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.