VLPart vs. CoDet: Compared and Contrasted

Compare VLPart and CoDet with Autodistill

Using Autodistill, you can compare VLPart 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-vlpart autodistill-codet

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


from autodistill_vlpart import VLPart
from autodistill_codet import CoDet

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

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

models = [
    VLPart(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"
)

‍

Models



VLPart vs. CoDet

Both

VLPart

and

CoDet

are commonly used in computer vision projects. Below, we compare and contrast

VLPart

and

CoDet

	VLPart	CoDet
Date of Release		Oct 24, 2023
Model Type	Object Detection	Object Detection
Architecture
GitHub Stars		79

Using Autodistill, you can compare VLPart 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-vlpart autodistill-codet

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


from autodistill_vlpart import VLPart
from autodistill_codet import CoDet

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

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

models = [
    VLPart(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"
)

‍

VLPart

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

How to Augment How to Label How to Plot Predictions How to Filter Predictions How to Create a Confusion Matrix

CoDet

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

How to Augment How to Label How to Plot Predictions How to Filter Predictions How to Create a Confusion Matrix

Learn more about CoDet

Compare VLPart to other models

Compare CoDet to other models

Deploy a computer vision model today

Join 250,000 developers curating high quality datasets and deploying better models with Roboflow.

Get started

VLPart vs. CoDet

Models

VLPart

CoDet

Compare VLPart and CoDet with Autodistill

Explore Models

By Task

By Feature

VLPart vs. CoDet

VLPart

CoDet

Compare VLPart to other models

Compare CoDet to other models

Deploy a computer vision model today