Try the Model

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

Overview

VLPart, developed by Meta Research, is an object detection and segmentation model that works with an open vocabulary. autodistill-vlpart enables you to use VLPart to auto-label images for use in training a fine-tuned model. autodistill-vlpart supports the LVIS vocabulary.

VLPart License

VLPart

is licensed under a

MIT License

license.

Performance

Deploy a VLPart API

You can use Roboflow Inference to deploy a

VLPart

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.

Label Data Automatically with VLPart

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

VLPart