yformer / EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Apache License 2.0
2.18k stars 154 forks source link

Integration to segment_anything package? #19

Open oranshayer opened 11 months ago

oranshayer commented 11 months ago

Hey,

Thanks for your work and model! Is there a plan to integrate this model to work with the segment_anything package, specifically with SamAutomaticMaskGenerator?

For example, this is how we use it today:

        self.sam = sam_model_registry["vit_h"](checkpoint=model_checkpoint_path).to(self.device)
        self.mask_generator = SamAutomaticMaskGenerator(self.sam, pred_iou_thresh=0.88, stability_score_thresh=0.8, min_mask_region_area=200)

will we be able to use the same with the EfficiantSAM model? Thanks!

yformer commented 11 months ago

Hi @oranshayer, thanks for your interest! Yes, we are planning EfficientSAM with the segment_anything package. We will let you know when it is ready.

AmitIsraeli commented 11 months ago

thank you very much waiting for it also (:

smandava98 commented 11 months ago

following

hadariru commented 5 months ago

following

yformer commented 15 hours ago

Hi @oranshayer, @AmitIsraeli, @smandava98, @hadariru, we have released efficient track anything for unified image and video segmentation. It is compatible to SAM2 package. Please check https://github.com/yformer/EfficientTAM