Language Segment-Anything is an open-source project that combines the power of instance segmentation and text prompts to generate masks for specific objects in images. Built on the recently released Meta model, Segment Anything Model 2, and the GroundingDINO detection model, it's an easy-to-use and effective tool for object detection and image segmentation.
- Zero-shot text-to-bbox approach for object detection.
- GroundingDINO detection model integration.
- SAM 2.1
- Batch inference support.
- Easy endpoint deployment using the Lightning AI litserve platform.
- Customizable text prompts for precise object segmentation.
- Python 3.11 or higher
Before installing lang-sam, please install PyTorch using the following command:
pip install torch==2.4.1 torchvision==0.19.1 --extra-index-url https://download.pytorch.org/whl/cu124
pip install -U git+https://github.com/luca-medeiros/lang-segment-anything.git
Or Clone the repository and install the required packages:
git clone https://github.com/luca-medeiros/lang-segment-anything && cd lang-segment-anything
pip install -e .
Build and run the image.
git clone https://github.com/luca-medeiros/lang-segment-anything && cd lang-segment-anything
docker build --tag lang-segment-anything:latest .
docker run --gpus all -p 8000:8000 lang-segment-anything:latest
To run the gradio APP:
python app.py
And open http://0.0.0.0:8000/gradio
Use as a library:
from PIL import Image
from lang_sam import LangSAM
model = LangSAM()
image_pil = Image.open("./assets/car.jpeg").convert("RGB")
text_prompt = "wheel."
results = model.predict([image_pil], [text_prompt])
This project is based on/used the following repositories:
This project is licensed under the Apache 2.0 License
