This repository contains the code supporting the OmdetTurbo base model for use with Autodistill.
OmdetTurbo, developed by Binjiang Institute of Zhejiang University, is a computer vision model for zero-shot detection in real time.
Read the full Autodistill documentation.
Read the Omdet-turbo Autodistill documentation.
To use OmdetTurbo with autodistill, you need to install the following dependency:
pip3 install autodistill-omdet_turbofrom autodistill_omdet_turbo import OmdetTurbo
from autodistill.detection import CaptionOntology
from autodistill.utils import plot
import cv2
# define an ontology to map class names to our OmdetTurbo 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 = OmdetTurbo(
ontology=CaptionOntology({"person": "person", "a forklift": "forklift"})
)
results = base_model.predict("iamge.png")
plot(
image=cv2.imread("image.png"),
classes=base_model.ontology.classes(),
detections=results,
)
base_model.label("./context_images", extension=".jpeg")This model is licensed under an Apache 2.0 (see original model implementation license, and the corresponding HuggingFace Transformers documentation).
We love your input! Please see the core Autodistill contributing guide to get started. Thank you 🙏 to all our contributors!