Deploy with Roboflow

YOLOR

YOLOR (You Only Learn One Representation) is an object detection model that uses both implicit and explicit knowledge to make predictions.

Try the Model

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

Overview

What is YOLOR?

You Only Learn One Representation (YOLOR) is a state-of-the-art object detection model. YOLOR pre-trains an implicit knowledge network with all of the tasks present in the COCO dataset, namely object detection, instance segmentation, panoptic segmentation, keypoint detection, stuff segmentation, image caption, multi-label image classification, and long-tail object recognition. When optimizing for the COCO dataset, YOLOR trains another set of parameters that represent explicit knowledge. For prediction, both implicit and explicit knowledge is used.

YOLOR Architecture

Vision Transformer Performance

This novel approach propels YOLOR to the state-of-the-art for object detection in the speed/accuracy tradeoff landscape.

Images in Courtesy of Wong-Kin-Yiu

YOLOR License

YOLOR

is licensed under a

GPL-3.0

license.

Performance

Deploy a YOLOR API

You can use Roboflow Inference to deploy a

YOLOR

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 YOLOR

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

No items found.