teklia-yolo 0.2.6

Scripts to train and evaluate YOLOv8 models

YOLO

Scripts to train and evaluate YOLOv8 models. Read the official documentation of this library at https://dla.pages.teklia.com/yolo/.

It is licensed under the AGPL-v3 license.

Development

For development and tests purpose it may be useful to install the project as a editable package with pip.

• Use a virtualenv (e.g. with virtualenvwrapper mkvirtualenv -a . yolo)
• Install yolo as a package (e.g. pip install -e .)

Linter

Code syntax is analyzed before submitting the code.
To run the linter tools suite you may use pre-commit.

pip install pre-commit
pre-commit run -a

Run tests

Tests are executed with tox using pytest. To install tox,

pip install tox
tox

To reload the test virtual environment you can use tox -r

Run a single test module: tox -- <test_path> Run a single test: tox -- <test_path>::<test_function>

Documentation

Install node dependencies:

npm install

Build the documentation using make antora. You can then write in Asciidoc in the relevant docs/*.adoc files, and use a small python server to see output from public/ using python -m http.server.

Writing documentation

This documentation is generated using Antora.

Linting

This documentation is subject to linting using doc8, integrated into pre-commit.

The linting rules that doc8 applies can be found on its documentation.