https://github.com/curt-park/yolo-world-with-efficientvit-sam

YOLO-World + EfficientViT SAM
https://github.com/curt-park/yolo-world-with-efficientvit-sam

Last synced: 30 days ago
JSON representation

YOLO-World + EfficientViT SAM

• Host: GitHub
• URL: https://github.com/curt-park/yolo-world-with-efficientvit-sam
• Owner: Curt-Park
• License: apache-2.0
• Created: 2024-02-14T15:55:16.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-18T15:23:09.000Z (over 1 year ago)
• Last Synced: 2024-11-15T19:35:19.974Z (11 months ago)
• Language: Python
• Homepage: https://huggingface.co/spaces/curt-park/yolo-world-with-efficientvit-sam
• Size: 3.88 MB
• Stars: 76
• Watchers: 2
• Forks: 9
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# YOLO-World + EfficientViT SAM

🤗 [HuggingFace Space](https://huggingface.co/spaces/curt-park/yolo-world-with-efficientvit-sam)

![example_0](https://github.com/Curt-Park/yolo-world-with-efficientvit-sam/assets/14961526/326bde19-d535-4be5-829e-782fce0c1d00)

## Prerequisites

This project is developed and tested on Python3.10.

```bash

# Create and activate a python 3.10 environment.

conda create -n yolo-world-with-efficientvit-sam python=3.10 -y

conda activate yolo-world-with-efficientvit-sam

# Setup packages.

make setup

```

## How to Run

```bash

python app.py

```

Open http://127.0.0.1:7860/ on your web browser.

![example_1](https://github.com/Curt-Park/yolo-world-with-efficientvit-sam/assets/14961526/9388e4ee-6f71-4428-b17c-d218fd059949)

## Core Components

### YOLO-World

[YOLO-World](https://github.com/AILab-CVC/YOLO-World) is an open-vocabulary object detection model with high efficiency.

On the challenging LVIS dataset, YOLO-World achieves 35.4 AP with 52.0 FPS on V100,

which outperforms many state-of-the-art methods in terms of both accuracy and speed.

![image](https://github.com/Curt-Park/yolo-world-with-efficientvit-sam/assets/14961526/8a4a17bd-918d-478a-8451-f58e4a2dce79)



### EfficientViT SAM

[EfficientViT SAM](https://github.com/mit-han-lab/efficientvit) is a new family of accelerated segment anything models.

Thanks to the lightweight and hardware-efficient core building block,

it delivers 48.9× measured TensorRT speedup on A100 GPU over SAM-ViT-H without sacrificing performance.





## Powered By

```

@misc{zhang2024efficientvitsam,

  title={EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss},

  author={Zhuoyang Zhang and Han Cai and Song Han},

  year={2024},

  eprint={2402.05008},

  archivePrefix={arXiv},

  primaryClass={cs.CV}

}

@article{cheng2024yolow,

  title={YOLO-World: Real-Time Open-Vocabulary Object Detection},

  author={Cheng, Tianheng and Song, Lin and Ge, Yixiao and Liu, Wenyu and Wang, Xinggang and Shan, Ying},

  journal={arXiv preprint arXiv:2401.17270},

  year={2024}

}

@article{cai2022efficientvit,

  title={Efficientvit: Enhanced linear attention for high-resolution low-computation visual recognition},

  author={Cai, Han and Gan, Chuang and Han, Song},

  journal={arXiv preprint arXiv:2205.14756},

  year={2022}

}

```