Try the Model

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

Overview

YOLO-NAS Pose is a keypoint detection and pose estimation model developed by Deci AI. You can use the YOLO-NAS Pose model to detect the poses of people or objects in an image or video. For example, you can identify the pose of a person as part of an exercise application, or the position of joints on a robotic arm for use in calibrating a robot arm.

‍

YOLO-NAS Pose on a Beetles Album. Sourced from this Medium Article.

‍

YOLO-NAS Pose License

YOLO-NAS Pose

is licensed under a

Apache-2.0

license.

Performance

Yolo-NAS Pose has state of the art performance, while also having extremely low latency. Compared to other Yolo models, YOLO-NAS Pose outperforms most in low latency situations.

‍

Deploy a YOLO-NAS Pose API

You can use Roboflow Inference to deploy a

YOLO-NAS Pose

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 YOLO-NAS Pose

You can automatically label a dataset using YOLO-NAS Pose 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 YOLO-NAS Pose to train a computer vision model.

No items found.