Autodistill FastSAM Module

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

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

[!NOTE]

When you first run this model, the installation process will start. Inference may take a few seconds (in testing, up to 30 seconds) while the model is downloaded and installed. Once the model is installed, inference will be much faster.

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")

License

This project is licensed under an Apache 2.0 license.

🏆 Contributing

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