Autodistill BLIP Module

This repository contains the code supporting the BLIP base model for use with Autodistill.

BLIP, developed by Salesforce, is a computer vision model that supports visual question answering and zero-shot classification. Autodistill supports classifying images using BLIP.

Read the full Autodistill documentation.

Read the BLIP Autodistill documentation.

Installation

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

pip3 install autodistill-blip

Quickstart

from autodistill_blip import BLIP

# define an ontology to map class names to our BLIP 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 = BLIP(
    ontology=CaptionOntology(
        {
            "person": "person",
            "a forklift": "forklift"
        }
    )
)
base_model.label("./context_images", extension=".jpeg")

License

This project is licensed under a 3-Clause BSD license.

🏆 Contributing

We love your input! Please see the core Autodistill contributing guide to get started. Thank you 🙏 to all our contributors!