Models
VLPart vs. OWL ViT

VLPart vs. OWL ViT

Both VLPart and OWL ViT are commonly used in computer vision projects. Below, we compare and contrast VLPart and OWL ViT.

Models

icon-model

VLPart

VLPart, developed by Meta Research, is an object detection and segmentation model that works with an open vocabulary
icon-model

OWL ViT

OWL-ViT is a transformer-based object detection model developed by Google Research.
Model Type
Object Detection
--
Object Detection
--
Model Features
Item 1 Info
Item 2 Info
Architecture
--
--
Frameworks
--
--
Annotation Format
Instance Segmentation
Instance Segmentation
GitHub Stars
--
--
License
MIT License
--
--
Training Notebook
Compare Alternatives
--
Compare with...

Compare VLPart and OWL ViT with Autodistill

Using Autodistill, you can compare VLPart and OWL ViT 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-vlpart autodistill-owl-vit

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


from autodistill_vlpart import VLPart
from autodistill_owl_vit import OWLViT

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

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

models = [
    VLPart(ontology=ontology),
    OWLViT(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"
)