ModelsObject Detection
YOLOv8
Object Detection
Real-Time Vision
Deploy with Roboflow

YOLOv8

YOLOv8 is a state-of-the-art object detection and image segmentation model created by Ultralytics, the developers of YOLOv5.
Ultralytics
•
GitHubGitHub
•
star
21.1k+
stars
•
AGPL-3.0
license
•
Developed by
Ultralytics
•
Released
Jan 10, 2023
•
Arxiv logo markPaper

Try the Model

Use the widget below to experiment with YOLOv8. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

YOLOv8 is a state-of-the-art object detection and image segmentation model created by Ultralytics, the developers of YOLOv5. YOLOv8, launched on January 10, 2023, features:

  • A new backbone network;
  • A design that makes it easy to compare model performance with older models in the YOLO family;
  • A new loss function and;
  • A new anchor-free detection head.

YOLOv8 Performance: Benchmarked on Roboflow 100

We benchmarked YOLOv8 on Roboflow 100, an object detection benchmark that analyzes the performance of a model in task-specific domains. Roboflow 100 is a method of effectively assessing the extent to which a model can generalize across different problems.

YOLOv8 vs. YOLOv5

We found that YOLOv8 scored a 80.2% mAP score on Roboflow 100, compared to 73.5% mean score on YOLOv5. This shows that YOLOv8 is significantly better at domain-specific tasks than Ultralytics’ YOLOv5 predecessor. We compared YOLOv5s and YOLOv8 in this analysis.

YOLOv8 Perfomance: Benchmarked on COCO

Model size
(pixels)		 mAPval
50-95		 Speed
CPU
(ms)		 Speed
T4 GPU
(ms)		 params
(M)		 FLOPs
(B)
YOLOv8n 640 37.3 - - 3.2 8.7
YOLOv8s 640 44.9 - - 11.2 28.6
YOLOv8m 640 50.2 - - 25.9 78.9
YOLOv8l 640 52.9 - - 43.7 165.2
YOLOv8x 640 53.9 - - 68.2 257.8

(The table above is sourced from the official YOLOv8 repository).

YOLOv8 License

YOLOv8

is licensed under a 

AGPL-3.0

license. 

Performance

Deploy a YOLOv8 API

You can use Roboflow Inference to deploy a

YOLOv8

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.

First, install Inference:‍


pip install inference

To try a demo with a model trained on the Microsoft COCO dataset, use:


import inference
model = inference.load_roboflow_model("yolov8n-640")
results = model.infer(image="YOUR_IMAGE.jpg")

Above, replace:

  • YOUR_IMAGE.jpg with the path to your image.

You can also run fine-tuned models with Inference.

Retrieve your Roboflow API key and save it in an environment variable called ROBOFLOW_API_KEY:


export ROBOFLOW_API_KEY="your-api-key"

To use your model, run the following code:


import inference
model = inference.load_roboflow_model("model-name/version")
results = model.infer(image="YOUR_IMAGE.jpg")

Above, replace:

Label Data Automatically with YOLOv8

You can automatically label a dataset using YOLOv8 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 YOLOv8 to train a computer vision model.

YOLOv8 Alternatives

Compare YOLOv8 Model Sizes

Deploy YOLOv8 in One Click
Explore what YOLOv8 can do in a fully interactive workflow. GPU-backed, no code required.
Deploy Now with free GPU
Rocket

Deploy to Production

Roboflow offers a range of SDKs with which you can deploy your model to production.
Deploy to...
Rocket

Build a Workflow

Use YOLOv8 to Build Computer Vision Pipelines and Applications
Images

Data

Augmentation GuideLabeling Guide
Flask

Training

Model OverviewTrain on ColabTrain on JupyterTrain on KaggleTrain on SageMakerSee Model AlternativesView Benchmarks
Screwdriver and Wrench

Utilities

Plot PredictionsFilter PredictionsBlur PredictionsCreate A Confusion MatrixUse SAHI for Small Object Detection
Code Compare

Compare to Related Models

Curious about how this model compares to others? Check out our model comparisons.
Compare with...
arrow progress

Convert Annotation Format

YOLOv8 uses the uses the YOLOv8 PyTorch TXT annotation format. If your annotation is in a different format, you can use Roboflow's annotation conversion tools to get your data into the right format.
Convert Data Between Formats

Architecture

YOLO, CNN

Frameworks

PyTorch

Annotation Format

YOLOv8 PyTorch TXT

Popular YOLOv8 Use Cases

No items found.

YOLOv8 Integrations

YOLOv8 to Active Learning Data Collector

Build a computer vision workflow that connects YOLOv8 to Active Learning Data Collector.

YOLOv8 to MQTT Publisher

Build a computer vision workflow that connects YOLOv8 to MQTT Publisher.

YOLOv8 to Kafka Publish

Build a computer vision workflow that connects YOLOv8 to Kafka Publish.

YOLOv8 to Azure Sink

Build a computer vision workflow that connects YOLOv8 to Azure Sink.

YOLOv8 to Webhook Publish

Build a computer vision workflow that connects YOLOv8 to Webhook Publish.

YOLOv8 to Super Annotator

Build a computer vision workflow that connects YOLOv8 to Super Annotator.

YOLOv8 to SMS

Build a computer vision workflow that connects YOLOv8 to SMS.

YOLOv8 to S3 Upload

Build a computer vision workflow that connects YOLOv8 to S3 Upload.

YOLOv8 to Roboflow Classification Model

Build a computer vision workflow that connects YOLOv8 to Roboflow Classification Model.

YOLOv8 to Roboflow Instance Segmentation Model

Build a computer vision workflow that connects YOLOv8 to Roboflow Instance Segmentation Model.

YOLOv8 to YOLOv9

Build a computer vision workflow that connects YOLOv8 to YOLOv9.

YOLOv8 to YOLOv5 Instance Segmentation

Build a computer vision workflow that connects YOLOv8 to YOLOv5 Instance Segmentation.

YOLOv8 to YOLO-NAS

Build a computer vision workflow that connects YOLOv8 to YOLO-NAS.

YOLOv8 to YOLOv5

Build a computer vision workflow that connects YOLOv8 to YOLOv5.

YOLOv8 to YOLOv8

Build a computer vision workflow that connects YOLOv8 to YOLOv8.

YOLOv7 Instance Segmentation to YOLOv8

Build a computer vision workflow that connects YOLOv7 Instance Segmentation to YOLOv8.

YOLOv9 to YOLOv8

Build a computer vision workflow that connects YOLOv9 to YOLOv8.

YOLOv8 to YOLOv7 Instance Segmentation

Build a computer vision workflow that connects YOLOv8 to YOLOv7 Instance Segmentation.

YOLOv8 to YOLOv8 Instance Segmentation

Build a computer vision workflow that connects YOLOv8 to YOLOv8 Instance Segmentation.

YOLOv8 to YOLOv8 Classification

Build a computer vision workflow that connects YOLOv8 to YOLOv8 Classification.

YOLO-NAS to YOLOv8

Build a computer vision workflow that connects YOLO-NAS to YOLOv8.

Roboflow Classification Model to YOLOv8

Build a computer vision workflow that connects Roboflow Classification Model to YOLOv8.

YOLOv5 Instance Segmentation to YOLOv8

Build a computer vision workflow that connects YOLOv5 Instance Segmentation to YOLOv8.

YOLOv8 Classification to YOLOv8

Build a computer vision workflow that connects YOLOv8 Classification to YOLOv8.

YOLOv5 to YOLOv8

Build a computer vision workflow that connects YOLOv5 to YOLOv8.

YOLOv8 to YOLOv8 Keypoint Detection

Build a computer vision workflow that connects YOLOv8 to YOLOv8 Keypoint Detection.

YOLOv8 to Roboflow Object Detection Model

Build a computer vision workflow that connects YOLOv8 to Roboflow Object Detection Model.

YOLOv8 Instance Segmentation to YOLOv8

Build a computer vision workflow that connects YOLOv8 Instance Segmentation to YOLOv8.

YOLOv8 Keypoint Detection to YOLOv8

Build a computer vision workflow that connects YOLOv8 Keypoint Detection to YOLOv8.

Explore This Model on Roboflow

YOLOv8 Models on Universe
Blog
Blog

YOLOv8 Models on Universe

Explore publicly available models trained using YOLOv8.
Train YOLOv8 on a Custom Dataset
Blog
Blog

Train YOLOv8 on a Custom Dataset

In this article, we walk through how to train a YOLOv8 object detection model using a custom dataset.
Launch: Deploy YOLOv8 with Roboflow
Blog
Blog

Launch: Deploy YOLOv8 with Roboflow

In this tutorial, we show how to upload your own YOLOv8 model weights to deploy on the Roboflow platform.
What's New in YOLOv8
Blog
Blog

What's New in YOLOv8

The field of computer vision advances with the newest release of YOLOv8, setting a new state of the art for object detection and instance segmentation.
Launch: YOLOv8 Models on Roboflow Universe
Blog
Blog

Launch: YOLOv8 Models on Roboflow Universe

Pre-trained YOLOv8 models are available on Roboflow Universe
How to Train YOLOv8 Object Detection on a Custom Dataset
Blog
Blog

How to Train YOLOv8 Object Detection on a Custom Dataset

In this article, we walk through how to train a YOLOv8 object detection model using a custom dataset.
Ready to get started?

Join over 1 million developers building with Roboflow

Try it for FreeTalk to Sales