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

SigLIP base model for use with Autodistill.
https://github.com/autodistill/autodistill-siglip

Last synced: 5 days ago
JSON representation

SigLIP base model for use with Autodistill.

• Host: GitHub
• URL: https://github.com/autodistill/autodistill-siglip
• Owner: autodistill
• Created: 2024-02-16T21:54:12.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-03-05T10:38:02.000Z (8 months ago)
• Last Synced: 2024-09-17T15:53:42.613Z (about 2 months ago)
• Language: Python
• Size: 9.77 KB
• Stars: 7
• Watchers: 4
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


  


    

      

    

  



# Autodistill SigLIP Module

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

[CLIP](https://github.com/openai/CLIP), developed by OpenAI, is a computer vision model trained using pairs of images and text. You can use CLIP with autodistill for image classification.

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

Read the [SigLIP Autodistill documentation](https://autodistill.github.io/autodistill/base_models/siglip/).

## Installation

To use SigLIP with autodistill, you need to install the following dependency:

```bash

pip3 install autodistill-siglip

```

## Quickstart

```python

from autodistill_siglip import SigLIP

from autodistill.detection import CaptionOntology

# define an ontology to map class names to our SigLIP 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

labels = ["person", "a forklift"]

base_model = SigLIP(

    ontology=CaptionOntology({item: item for item in labels})

)

results = base_model.predict("image.jpeg", confidence=0.1)

top_1 = results.get_top_k(1)

# show top label

print(labels[top_1[0][0]])

# label folder of images

base_model.label("./context_images", extension=".jpeg")

```

## License

The SigLIP model is licensed under an [Apache 2.0 license](https://huggingface.co/google/siglip-base-patch16-224).

## 🏆 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!