First, install Autodistill and Autodistill OWL-ViT:
pip install autodistill autodistill-owl-vit
Then, run:
from autodistill_owl_vit import OWLViT
from autodistill.detection import CaptionOntology
# 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"
}
)
)
result = base_model.predict("image.jpeg")
print(result)