search

ziqi-jin / finetune-anything

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
MIT License
749 stars 54 forks source link

Implement EfficientSAM or MobileSAM #49

Open Sharpz7 opened 8 months ago

Sharpz7 commented 8 months ago

https://github.com/yformer/EfficientSAM https://github.com/ChaoningZhang/MobileSAM

I am not too sure how to implement EfficientSAM, but I do think I know how to implement MobileSAM, by replacing the full VIT model with Tiny-VIT.

You can see how that is done on another repo here https://github.com/ZrrSkywalker/Personalize-SAM/pull/35

And the code that I think needs changed https://github.com/ziqi-jin/finetune-anything/blob/main/extend_sam/segment_anything_ori/build_sam.py

ziqi-jin commented 8 months ago

thanks for your advice~

ziqi-jin commented 8 months ago

But it is a little hard for me to update code recently, coz the limitation of computing resource. I am fixing that

Sharpz7 commented 8 months ago

Hey, I am hoping to get to this myself - but MobileSAM would help fix your computing resources problem :))