README.md

---
title: Segment Anything
emoji: 🚀
colorFrom: gray
colorTo: pink
sdk: gradio
sdk_version: 3.25.0
app_file: app.py
pinned: false
---

# Segment Anything WebUI

[![Duplicate this Space](https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-sm.svg)](https://huggingface.co/spaces/AIBoy1993/segment_anything_webui?duplicate=true) 
[![Duplicate this Space](https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-sm-dark.svg)](https://huggingface.co/spaces/AIBoy1993/segment_anything_webui?duplicate=true)

This project is based on **[Segment Anything Model](https://segment-anything.com/)** by Meta. The UI is based on [Gradio](https://gradio.app/). 

- Try deme on HF: [AIBoy1993/segment_anything_webui](https://huggingface.co/spaces/AIBoy1993/segment_anything_webui)
- [GitHub](https://github.com/5663015/segment_anything_webui)

![](./images/20230408023615.png)

## Change Logs

- [2023-4-11] 
  - Support video segmentation. A short video can be automatically segmented by SAM.
  - Support text prompt segmentation using [OWL-ViT](https://huggingface.co/docs/transformers/v4.27.2/en/model_doc/owlvit#overview) (Vision Transformer for Open-World Localization) model.


## **Usage**

Following usage is running on your computer. 

- Install Segment Anything（[more details about install Segment Anything](https://github.com/facebookresearch/segment-anything#installation)）：

```
pip install git+https://github.com/facebookresearch/segment-anything.git
```

- `git clone` this repository：

```
git clone https://github.com/5663015/segment_anything_webui.git
```

- Make a new folder named `checkpoints` under this project，and put the downloaded weights files in `checkpoints`。You can download the weights using following URLs：

  - `vit_h`: [ViT-H SAM model](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth)

  - `vit_l`: [ViT-L SAM model](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth)

  - `vit_b`: [ViT-B SAM model](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth)

- Under `checkpoints`, make a new folder named `models--google--owlvit-base-patch32`, and put the downloaded [OWL-ViT weights](https://huggingface.co/google/owlvit-base-patch32) files in `models--google--owlvit-base-patch32`. 
- Run：

```
python app.py
```

**Note：** Default model is `vit_b`，the demo can run on CPU. Default device is `cpu`。

## TODO

- [x] Video segmentation

- [x] Add text prompt

- [ ] Add segmentation prompt (point and box)

## Reference

- Thanks to the wonderful work [Segment Anything](https://segment-anything.com/) and [OWL-ViT](https://arxiv.org/abs/2205.06230)
- Some video processing code references [kadirnar/segment-anything-video](https://github.com/kadirnar/segment-anything-video), and some OWL-ViT code references [ngthanhtin/owlvit_segment_anything](https://github.com/ngthanhtin/owlvit_segment_anything).