https://github.com/autodistill/autodistill-efficientsam

EfficientSAM base model for use with Autodistill.
https://github.com/autodistill/autodistill-efficientsam

autodistill efficientsam image-segmentation

Last synced: about 2 months ago
JSON representation

EfficientSAM base model for use with Autodistill.

• Host: GitHub
• URL: https://github.com/autodistill/autodistill-efficientsam
• Owner: autodistill
• License: apache-2.0
• Created: 2023-12-06T07:18:39.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-16T18:37:09.000Z (11 months ago)
• Last Synced: 2024-02-17T19:42:33.677Z (10 months ago)
• Topics: autodistill, efficientsam, image-segmentation
• Language: Python
• Homepage: https://docs.autodistill.com
• Size: 12.7 KB
• Stars: 0
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  


    

      

    

  



# Autodistill EfficientSAM Module

This repository contains the code supporting the EfficientSAM base model for use with [Autodistill](https://github.com/autodistill/autodistill).

[EfficientSAM](https://github.com/yformer/EfficientSAM) is an image segmentation model that was introduced in the paper "[EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://yformer.github.io/efficient-sam/)". You can use EfficientSAM with autodistill for image segmentation.

Read the full [Autodistill documentation](https://autodistill.github.io/autodistill/).

## Installation

To use EfficientSAM with Autodistill, you need to install the following dependency:

```bash

pip3 install autodistill-efficientsam

```

## Quickstart

This model returns segmentation masks for all objects in an image.

If you want segmentation masks only for specific objects matching a text prompt, we recommend combining EfficientSAM with a zero-shot detection model like GroundingDINO.

Read our ComposedDetectionModel documentation for more information about how to combine models like EfficientSAM and GroundingDINO.

```python

from autodistill_efficientsam import EfficientSAM

# define an ontology to map class names to our EfficientSAM prompt

# the ontology dictionary has the format {caption: class}

# where caption is the prompt sent to the base model, and class is the label that will

# be saved for that caption in the generated annotations

# then, load the model

base_model = EfficientSAM(None)

masks = base_model.predict("./image.png")

```

## License

This project is licensed under an [Apache 2.0 license](LICENSE).

## 🏆 Contributing

We love your input! Please see the core Autodistill [contributing guide](https://github.com/autodistill/autodistill/blob/main/CONTRIBUTING.md) to get started. Thank you 🙏 to all our contributors!