Deploy with Roboflow

YOLOv8

YOLOv8 is a state-of-the-art object detection and image segmentation model created by Ultralytics, the developers of YOLOv5.

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)	mAP^val 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).

Performance

Use This Model

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:

YOUR_IMAGE.jpg with the path to your image.
model_id/version with the YOLOv8 model ID and version you want to use. Learn how to retrieve your model and version ID.

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.

Grounding DINO and YOLOv8

SAM-CLIP and YOLOv8

Grounded SAM and YOLOv8

Popular YOLOv8 Use Cases

YOLOv8
SMS

Detect safety equipment with computer vision

Add to workspace

YOLOv8
Clip Comparison

Detect and classify objects on a retail shelf

Add to workspace

YOLOv8
MQTT Publisher

Detect metal scratches with computer vision

Add to workspace

YOLOv8
CSV Sink

Detect glass defects with computer vision

Add to workspace

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

Blog

YOLOv8

Overview

YOLOv8 Performance: Benchmarked on Roboflow 100

YOLOv8 vs. YOLOv5

YOLOv8 Perfomance: Benchmarked on COCO

Performance

Use This Model

Label Data Automatically with YOLOv8

Deploy to Production

Build a Workflow

Data

Training

Utilities

Compare to Related Models

Convert Annotation Format

Architecture

Frameworks

Annotation Format

Popular YOLOv8 Use Cases

YOLOv8 Integrations

YOLOv8 to Active Learning Data Collector

YOLOv8 to MQTT Publisher

YOLOv8 to Kafka Publish

YOLOv8 to Azure Sink

YOLOv8 to Webhook Publish

YOLOv8 to Super Annotator

YOLOv8 to SMS

YOLOv8 to S3 Upload

YOLOv8 to Roboflow Classification Model

YOLOv8 to Roboflow Instance Segmentation Model

YOLOv8 to YOLOv9

YOLOv8 to YOLOv5 Instance Segmentation

YOLOv8 to YOLO-NAS

YOLOv8 to YOLOv5

YOLOv8 to YOLOv8

YOLOv7 Instance Segmentation to YOLOv8

YOLOv9 to YOLOv8

YOLOv8 to YOLOv7 Instance Segmentation

YOLOv8 to YOLOv8 Instance Segmentation

YOLOv8 to YOLOv8 Classification

YOLO-NAS to YOLOv8

Roboflow Classification Model to YOLOv8

YOLOv5 Instance Segmentation to YOLOv8

YOLOv8 Classification to YOLOv8

YOLOv5 to YOLOv8

YOLOv8 to YOLOv8 Keypoint Detection

YOLOv8 to Roboflow Object Detection Model

YOLOv8 Instance Segmentation to YOLOv8

YOLOv8 Keypoint Detection to YOLOv8

Explore This Model on Roboflow

YOLOv8 Models on Universe

Train YOLOv8 on a Custom Dataset

Launch: Deploy YOLOv8 with Roboflow

What's New in YOLOv8

Launch: YOLOv8 Models on Roboflow Universe

How to Train YOLOv8 Object Detection on a Custom Dataset

Join over 500,000 developers building with Roboflow