YOLOv8 just released! New features and get started

Ultralytics just released YOLOv8, a state-of-the-art model that builds on the success of previous YOLO versions and includes new features and improvements to further increase its performance and versatility. This model is fast, accurate, and easy to use, making it a great choice for a variety of object detection, image segmentation, and image classification tasks.

Installation

The recommended installation is by pip install.

 
pip install ultralytics

Alternatively, clone the project.

 
git clone https://github.com/ultralytics/ultralytics
cd ultralytics
pip install -e '.[dev]'

Get started

See contributing section to know more about contributing to the project vai CLI or a Python API.

CLI

 
yolo task=detect    mode=train    model=yolov8n.yaml      args...
          classify       predict        yolov8n-cls.yaml  args...
          segment        val            yolov8n-seg.yaml  args...
                         export         yolov8n.pt        format=onnx  args...

Python API

 
from ultralytics import YOLO

model = YOLO('yolov8n.yaml')                # build a new model from scratch
model = YOLO('yolov8n.pt')                  # load a pretrained model (recommended for best training results)
results = model.train(data='coco128.yaml')  # train the model
results = model.val()                       # evaluate model performance on the validation set
results = model.predict(source='bus.jpg')   # predict on an image
success = model.export(format='onnx')       # export the model to ONNX format

Accelerate YOLOv8 inference time by 5x with Speedster

YOLOv8 can be further optimized to reduce inference time by over 5x. The acceleration is achieved by compiling the model onto the hardware and applying specific optimization techniques that further boost inference computing with Speedster.

Speedster is an open-source App designed to speed up AI inference in just a few lines of code. The library boosts your model to achieve the maximum acceleration that is physically possible on your hardware. At this link you can find a notebook on how to accelerate YOLOv8.

License

YOLOv8 comes with two licenses: GPL-3.0 License, and an Enterprise License that provides greater flexibility for commercial product development without the open-source requirements of GPL-3.0.

Useful links

• Speedster, open source library to automatically apply SOTA optimization techniques to achieve the maximum inference speed-up on your hardware.
• YOLOv8 documentation
• YOLOv8 checkpoints