annotation-ai/technical-demo

Technical Demos

This is a repository for a collection of technical demos made by Annotation-AI.

Segment Everything: CPU acceleration and promptable applications

Summary

Every demo doesn't use GPU resources, and they are served on CPU only instances.

• Video
• Demo1 (Everything) / Demo2 (Text) / Demo3 (Image) / Demo4 (Drawing) / Demo5 (Click)

Background

One of the most appealing applications of Segment Anything Model (SAM) is Everything, which detects and segments all objects in an image. However, it requires 1,024 inferences per a single image, and due to the reason, it is hard to be feasible for service providers who don’t have massive GPU resources. In order to handle this issue, we re-implemented the Everything algorithm in iterative manner that is better for CPU only environments. Mostly, we can expect comparable results to the original Everything within 1/5 number of inferences (e.g. 1024 vs 200), and it takes under 10 seconds to search for masks on a CPU upgrade instance (8 vCPU, 32GB RAM) of Huggingface space.

We named it Fast Segment Everything. You can run the DEMO in HuggingFace Space.

Applications: Promptable Segmentation

Based on Fast Segment Everything algorithm, we built a number of applications for promptable segmentation.: text, image, drawing, and click.

Title	GIF	Demo
Segment everything with a text prompt		HuggingFace Space
Segment everything with an image prompt		HuggingFace Space
Segment everything with a drawing prompt		HuggingFace Space
Segment similar things! (Single click)		HuggingFace Space

Person Re-Identification(Re-ID)

Person re-identification(Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. We implement Re-ID applications for various situations.

Title	GIF	Demo
Re-ID with query & gallery images		HuggingFace Space

technical-demo's Issues

Fast Segment Everything with a text prompt (without GPU)？

I didn't have any reaction when I used it

When duplicate the space in hugging face, it cannot find the related github repo

@nicewook @Curt-Park @dev-annotation-ai @DonghanKimAAI

Cannot find this https://github.com/annotation-ai/mlwiz-technical-demo/ when I duplicate the space in hugginface . Did you make this repo private? Please make it public so that the huggingface space could be duplicate. (I think similar problem for other examples / demos

Model Source Code

I want to use the HF space for my own personal needs.
I tried to get the models from Docker, and it seems that no code is available.
It would be much appreciated if I could get some help.
Thanks!