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

ALBEF, developed by Salesforce, is a computer vision model that supports a range of tasks, including image-text pre-training, image-text retrieval, visual question anserting, and zero-shot classification. You can classify images using ALBEF with Autodistill.

Read the full Autodistill documentation.

Read the ALBEF Autodistill documentation.

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

pip3 install autodistill-albef

from autodistill_albef import ALBEF

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

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

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