Try the Model

Use the widget below to experiment with OWLv2. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

OWLv2 is a transformer-based object detection model developed by Google Research. OWLv2 is the successor to OWL ViT.

‍

OWLv2 License

OWLv2

is licensed under a

license.

Performance

Deploy a OWLv2 API

You can use Roboflow Inference to deploy a

OWLv2

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

First, install Autodistill and Autodistill OWLv2:


pip install autodistill autodistill-owlv2

Then, run:


from autodistill_owlv2 import OWLv2
from autodistill.detection import CaptionOntology
from autodistill.utils import plot
import cv2

# define an ontology to map class names to our OWLv2 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 = OWLv2(
    ontology=CaptionOntology(
        {
            "person": "person",
            "dog": "dog"
        }
    )
)

# run inference on a single image
results = base_model.predict("dog.jpeg")

plot(
    image=cv2.imread("dog.jpeg"),
    classes=base_model.ontology.classes(),
    detections=results
)

‍

Label Data Automatically with OWLv2

You can automatically label a dataset using OWLv2 with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use OWLv2 to train a computer vision model.

OWLv2