Models
VLPart vs. LLaVA

VLPart vs. LLaVA

Both VLPart and LLaVA-1.5 are commonly used in computer vision projects. Below, we compare and contrast VLPart and LLaVA-1.5.

Models

icon-model

VLPart

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

LLaVA-1.5

LLaVA is an open source multimodal language model that you can use for visual question answering and has limited support for object detection.
Model Type
Object Detection
--
Object Detection
--
Model Features
Item 1 Info
Item 2 Info
Architecture
--
--
Frameworks
--
--
Annotation Format
Instance Segmentation
Instance Segmentation
GitHub Stars
--
16,000
--
License
MIT License
--
Apache-2.0
--
Training Notebook
Compare Alternatives

Compare VLPart and LLaVA-1.5 with Autodistill

Using Autodistill, you can compare VLPart and LLaVA 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-llava

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


from autodistill_vlpart import VLPart
from autodistill_llava import LLaVA

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

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

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

Compare VLPart vs. LLaVA

Provide your own image below to test YOLOv8 and YOLOv9 model checkpoints trained on the Microsoft COCO dataset.

COCO can detect 80 common objects, including cats, cell phones, and cars.