OWL ViT vs. CoDet: Compared and Contrasted

Models

OWL ViT

OWL-ViT is a transformer-based object detection model developed by Google Research.

Learn more about OWL ViT

CoDet

CoDet is an open vocabulary zero-shot object detection model.

Learn more about CoDet

Model Type

Object Detection

Model Features

Item 1 Info

Item 2 Info

Architecture

Annotation Format

Instance Segmentation

Framework

GitHub

View Repo

GitHub Stars

License

Apache 2.0

Apache 2.0 License

Paper

View Paper

Training Notebook

Train on Colab

Deploy Model

Deploy with Roboflow

Compare Alternatives

Compare OWL ViT and CoDet with Autodistill

Using Autodistill, you can compare OWL ViT and CoDet on your own images in a few lines of code.

Here is an example comparison:

To start a comparison, first install the required dependencies:


pip install autodistill autodistill-owl-vit autodistill-codet

Next, create a new Python file and add the following code:


from autodistill_owl_vit import OWLViT
from autodistill_codet import CoDet

from autodistill.detection import CaptionOntology
from autodistill.utils import compare

ontology = CaptionOntology(
    {
        "solar panel": "solar panel",
    }
)

models = [
    OWLViT(ontology=ontology),
    CoDet(ontology=ontology)
]

images = [
    "/home/user/autodistill/solarpanel1.jpg",
    "/home/user/autodistill/solarpanel2.jpg"
]

compare(
    models=models,
    images=images
)

Above, replace the images in the `images` directory with the images you want to use.

The images must be absolute paths.

Then, run the script.

You should see a model comparison like this:

When you have chosen a model that works best for your use case, you can auto label a folder of images using the following code:


base_model.label(
  input_folder="./images",
  output_folder="./dataset",
  extension=".jpg"
)

‍

OWL ViT vs. CoDet

Models

OWL ViT

CoDet

Compare OWL ViT and CoDet with Autodistill

Compare OWL ViT vs. CoDet