Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

For alternative installation methods including Conda, Docker, and Git, please refer to the Quickstart Guide.

YOLOv8 may be used directly in the Command Line Interface (CLI) with a yolo command:

yolo predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg'

yolo can be used for a variety of tasks and modes and accepts additional arguments, i.e. imgsz=640. See the YOLOv8 CLI Docs for examples.

YOLOv8 may also be used directly in a Python environment, and accepts the same arguments as in the CLI example above:

from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n.yaml")  # build a new model from scratch
model = YOLO("yolov8n.pt")  # load a pretrained model (recommended for training)

# Use the model
model.train(data="coco8.yaml", epochs=3)  # train the model
metrics = model.val()  # evaluate model performance on the validation set
results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
path = model.export(format="onnx")  # export the model to ONNX format

See YOLOv8 Python Docs for more examples.

See Detection Docs for usage examples with these models trained on COCO, which include 80 pre-trained classes.

• mAP^val values are for single-model single-scale on COCO val2017 dataset.
  Reproduce by yolo val detect data=coco.yaml device=0
• Speed averaged over COCO val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val detect data=coco.yaml batch=1 device=0|cpu

See Detection Docs for usage examples with these models trained on Open Image V7, which include 600 pre-trained classes.

• mAP^val values are for single-model single-scale on Open Image V7 dataset.
  Reproduce by yolo val detect data=open-images-v7.yaml device=0
• Speed averaged over Open Image V7 val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val detect data=open-images-v7.yaml batch=1 device=0|cpu

See Segmentation Docs for usage examples with these models trained on COCO-Seg, which include 80 pre-trained classes.

• mAP^val values are for single-model single-scale on COCO val2017 dataset.
  Reproduce by yolo val segment data=coco-seg.yaml device=0
• Speed averaged over COCO val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val segment data=coco-seg.yaml batch=1 device=0|cpu

See Pose Docs for usage examples with these models trained on COCO-Pose, which include 1 pre-trained class, person.

• mAP^val values are for single-model single-scale on COCO Keypoints val2017 dataset.
  Reproduce by yolo val pose data=coco-pose.yaml device=0
• Speed averaged over COCO val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val pose data=coco-pose.yaml batch=1 device=0|cpu

See OBB Docs for usage examples with these models trained on DOTAv1, which include 15 pre-trained classes.

• mAP^test values are for single-model multiscale on DOTAv1 dataset.
  Reproduce by yolo val obb data=DOTAv1.yaml device=0 split=test and submit merged results to DOTA evaluation.
• Speed averaged over DOTAv1 val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu

See Classification Docs for usage examples with these models trained on ImageNet, which include 1000 pretrained classes.

• acc values are model accuracies on the ImageNet dataset validation set.
  Reproduce by yolo val classify data=path/to/ImageNet device=0
• Speed averaged over ImageNet val images using an Amazon EC2 P4d instance.
  Reproduce by yolo val classify data=path/to/ImageNet batch=1 device=0|cpu