You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
Glenn Jocher 48cffa176e
Shorten module paths with new 'nn' dir (#96)
2 years ago
.github Import YOLOv5 dataloader (#94) 2 years ago
docs Rename `img_size` to `imgsz` (#86) 2 years ago
ultralytics Shorten module paths with new 'nn' dir (#96) 2 years ago
.gitignore Cli support (#50) 2 years ago
.pre-commit-config.yaml DDP and new dataloader Fix (#95) 2 years ago
CITATION.cff Fix CITATION.cff typos (#64) 2 years ago
CONTRIBUTING.md docs setup (#61) 2 years ago
LICENSE Initial commit 2 years ago
MANIFEST.in Trainer + Dataloaders (#27) 2 years ago
README.md Cli support (#50) 2 years ago
mkdocs.yml Update docs (#71) 2 years ago
requirements.txt YOLOv5 updates (#90) 2 years ago
setup.cfg Flake8 updates (#66) 2 years ago
setup.py docs setup (#61) 2 years ago

README.md

Ultralytics CI

Install

pip install ultralytics

Development

git clone https://github.com/ultralytics/ultralytics
cd ultralytics
pip install -e .

Usage

1. CLI

To simply use the latest Ultralytics YOLO models

yolo task=detect    mode=train  model=s.yaml ...
          classify       infer        s-cls.yaml
          segment        val          s-seg.yaml

2. Python SDK

To use pythonic interface of Ultralytics YOLO model

import ultralytics
from ultralytics import YOLO

model = YOLO()
model.new("s-seg.yaml") # automatically detects task type
model.load("s-seg.pt") # load checkpoint
model.train(data="coco128-segments", epochs=1, lr0=0.01, ...)

If you're looking to modify YOLO for R&D or to build on top of it, refer to Using Trainer Guide on our docs.