Try the Model

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

Overview

YOLACT is a simple, fully convolutional model for real-time instance segmentation

YOLACT License

YOLACT

is licensed under a

MIT

license.

Performance

Deploy a YOLACT API

You can use Roboflow Inference to deploy a

YOLACT

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 YOLACT

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

No items found.