https://github.com/autodistill/autodistill-owl-vit

OWL-ViT module for Autodistill.
https://github.com/autodistill/autodistill-owl-vit

autodistill owl-vit vision-transformers

Last synced: 5 days ago
JSON representation

OWL-ViT module for Autodistill.

• Host: GitHub
• URL: https://github.com/autodistill/autodistill-owl-vit
• Owner: autodistill
• License: apache-2.0
• Created: 2023-06-06T08:40:02.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-02T15:50:00.000Z (10 days ago)
• Last Synced: 2024-11-02T16:28:39.174Z (10 days ago)
• Topics: autodistill, owl-vit, vision-transformers
• Language: Python
• Homepage: https://autodistill.com
• Size: 10.7 KB
• Stars: 5
• Watchers: 4
• Forks: 2
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  


    

      

    

  



# Autodistill OWL-ViT Module

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

[OWL-ViT](https://huggingface.co/google/owlvit-base-patch32) is a transformer-based object detection model developed by Google Research.

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

Read the [OWL-ViT Autodistill documentation](https://autodistill.github.io/autodistill/base_models/owlvit/).

## Installation

To use OWL-ViT with autodistill, you need to install the following dependency:

```bash

pip3 install autodistill-owl-vit

```

## Quickstart

```python

from autodistill_owl_vit import OWLViT

# define an ontology to map class names to our OWLViT 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 = OWLViT(

    ontology=CaptionOntology(

        {

            "person": "person",

            "a forklift": "forklift"

        }

    )

)

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

```

## License

The code in this repository 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!