EvaCLIP

Classification Base Model Community Contribution

What is EvaCLIP?

Note: This module was contributed by a third-party community member unaffiliated with Roboflow.

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

EvaCLIP, is a computer vision model trained using pairs of images and text. It can be used for classification of images.

Installation

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

pip3 install autodistill-evaclip

Quickstart

from autodistill_evaclip import EvaCLIP
from autodistill.detection import CaptionOntology

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

results = base_model.predict("./context_images/test.jpg")

print(results)

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