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