1. Introduction to YOLOV8
`YOLOv8` 是来自 Ultralytics 的最新的基于 YOLO 的对象检测模型系列,提供最先进的性能。
Ultralytics YOLOv8, the latest version of the real-time object detection and image segmentation model. YOLOv8 builds on cutting-edge advances in deep learning and computer vision to deliver unrivaled performance in speed and accuracy. Its streamlined design makes it suitable for a variety of applications and easily adapts to different hardware platforms, from edge devices to cloud APIs. Compared with previous YOLO
versions , YOLOv8
the model is faster and more accurate, while providing a unified framework for training models.
- Support task type
Model Type | Pre-trained Weights | Task |
---|---|---|
YOLOv8 | yolov8n.pt , yolov8s.pt , yolov8m.pt , yolov8l.pt , yolov8x.pt |
Detection |
YOLOv8-seg | yolov8n-seg.pt , yolov8s-seg.pt , yolov8m-seg.pt , yolov8l-seg.pt , yolov8x-seg.pt |
Instance Segmentation |
YOLOv8-pose | yolov8n-pose.pt , yolov8s-pose.pt , yolov8m-pose.pt , yolov8l-pose.pt , yolov8x-pose.pt ,yolov8x-pose-p6 |
Pose/Keypoints |
YOLOv8-cls | yolov8n-cls.pt , yolov8s-cls.pt , yolov8m-cls.pt , yolov8l-cls.pt , yolov8x-cls.pt |
Classification |
- Support mode type
Mode | Supported |
---|---|
Inference | ✔ |
Validation | ✔ |
Training | ✔ |
Note : Ultralytics recently introduced segment-anything
instance segmentation in conjunction with
Segment Anything
from ultralytics.vit import SAM
model = SAM("sam_b.pt")
model.info() # display model information
model.predict(...) # train the model
- Support task type
Model Type | Pre-trained Weights | Tasks Supported |
---|---|---|
sam base | sam_b.pt |
Instance Segmentation |
sam large | sam_l.pt |
Instance Segmentation |
- Support mode type
Mode | Supported |
---|---|
Inference | ✔ |
Validation | ❌ |
Training | ❌ |
2. Install and configure YOLOV8
ultralytics
Support command line interface (CLI) API and Python SDK, which can be installed through pip, the installation command is as follows:
pip install ultralytics
- For developers, they can git clone the source code, and then configure and install related dependencies in requirements.txt :
git clone https://github.com/ultralytics/ultralytics
cd ultralytics
pip install -r requirements.txt
note : YOLOV8 dependencies include pytorch
related libraries, but the requirements vary PyTorch
depending on the operating system and requirements, so it is recommended to install and related dependencies according to the instructions on the Pytorch official website .CUDA
PyTorch