Try the Model

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

Overview

Grounding DINO is a state-of-the-art zero-shot object detection model.

‍

Grounding DINO License

Grounding DINO

is licensed under a

Apache-2.0

license.

Performance

Deploy a Grounding DINO API

You can use Roboflow Inference to deploy a

Grounding DINO

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 the Inference Grounding DINO extension:

pip install "inference[grounding-dino]"

Create a new Python file called app.py and add the following code:


from inference.models.grounding_dino import GroundingDINO

model = GroundingDINO(api_key="")

results = model.infer(
    {
        "image": {
            "type": "url",
            "value": "https://media.roboflow.com/fruit.png",
        },
        "text": ["apple"]
    }
)

print(results.json())

In this code, we load Grounding DINO, run Grounding DINO on an image, and annotate the image with the predictions from the model.

Label Data Automatically with Grounding DINO

You can automatically label a dataset using Grounding DINO 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 Grounding DINO to train a computer vision model.

Grounding DINO