Overview

MetaCLIP is a zero-shot classification and embedding model developed by Meta AI.

‍

Performance

Use This Model

First, install Autodistill and Autodistill MetaCLP:


pip install autodistill autodistill-metaclip

Then, run:


from autodistill_metaclip import MetaCLIP

# define an ontology to map class names to our MetaCLIP 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 = MetaCLIP(
    ontology=CaptionOntology(
        {
            "person": "person",
            "a forklift": "forklift"
        }
    )
)

results = base_model.predict("./image.png")
print(results)

‍

Label Data Automatically with MetaCLIP

You can automatically label a dataset using MetaCLIP with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use MetaCLIP to train a computer vision model.

No items found.