EfficientSAM

Efficient Grounded-SAM

We're going to combine Grounding-DINO with efficient SAM variants for faster annotating.

Table of Contents

• Installation
• Efficient SAM Series
• Run Grounded-FastSAM Demo
• Run Grounded-MobileSAM Demo

Installation

• Install Grounded-SAM

• Install Fast-SAM

Efficient SAMs

Here's the list of Efficient SAM variants:

Title	Intro	Description	Links
FastSAM		The Fast Segment Anything Model(FastSAM) is a CNN Segment Anything Model trained by only 2% of the SA-1B dataset published by SAM authors. The FastSAM achieve a comparable performance with the SAM method at 50× higher run-time speed.	[Github] [Demo]
MobileSAM		MobileSAM performs on par with the original SAM (at least visually) and keeps exactly the same pipeline as the original SAM except for a change on the image encoder. Specifically, we replace the original heavyweight ViT-H encoder (632M) with a much smaller Tiny-ViT (5M). On a single GPU, MobileSAM runs around 12ms per image: 8ms on the image encoder and 4ms on the mask decoder.	[Github]

Run Grounded-FastSAM Demo

• Firstly, download the pretrained Fast-SAM weight here

• Run the demo with the following script:

cd Grounded-Segment-Anything

python EfficientSAM/grounded_fast_sam.py --model_path "./FastSAM-x.pt" --img_path "assets/demo4.jpg" --text "the black dog." --output "./output/"

• And the results will be saved in ./output/ as:

Input	Text	Output
	"The black dog."

Note: Due to the post process of FastSAM, only one box can be annotated at a time, if there're multiple box prompts, we simply save multiple annotate images to ./output now, which will be modified in the future release.

Run Grounded-MobileSAM Demo

• Firstly, download the pretrained MobileSAM weight here

• Run the demo with the following script:

cd Grounded-Segment-Anything

python EfficientSAM/grounded_mobile_sam.py

• And the result will be saved as ./gronded_mobile_sam_anontated_image.jpg as:

Input	Text	Output
	"The running dog"