FastSAM

FastSAM is a segmentation model trained on 2% of the SA-1B dataset used to train the Segment Anything Model.

Read the full Autodistill documentation.

Read the FastSAM Autodistill documentation.

Installation

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

pip3 install autodistill-fastsam

Quickstart

from autodistill_fastsam import FastSAM

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