Metadata-Version: 2.1
Name: boml
Version: 0.1.2a1
Summary: A Bilevel Optimizer Library in Python for Meta Learning
Home-page: https://github.com/dut-media-lab/BOML
Author: Yaohua Liu, Risheng Liu
Author-email: liuyaohua@mail.dlut.edu.cn
License: MIT
Keywords: meta-learning,bilevel-optimization,few-shot-lerning,python,Deep learning
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Requires-Python: >=3.5,<3.8
Requires-Dist: imageio
Requires-Dist: h5py
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: intervaltree
Requires-Dist: matplotlib
Requires-Dist: Pillow
Requires-Dist: scikit-learn
Requires-Dist: tensorflow (<=1.15.*,>=1.13.*)

.. BOML documentation master file, created by
   sphinx-quickstart on Mon Sep  7 09:30:26 2020.
   You can adapt this file completely to your liking, but it should at least
   contain the root `toctree` directive.

Welcome to BOML's documentation!
================================
**Configuration & Status**

.. image:: https://travis-ci.com/dut-media-lab/BOML.svg?branch=master
   :target: https://github.com/dut-media-lab/BOML
   :alt: build status

.. image:: https://codecov.io/gh/dut-media-lab/BOML/branch/master/graph/badge.svg
   :target: https://github.com/dut-media-lab/BOML
   :alt: codecov

.. image:: https://readthedocs.org/projects/pybml/badge/?version=latest
   :target: https://github.com/dut-media-lab/BOML
   :alt: Documentation Status

.. image:: https://img.shields.io/badge/license-MIT-000000.svg
   :target: https://github.com/dut-media-lab/BOML
   :alt: License

.. image:: https://img.shields.io/github/languages/top/dut-media-lab/BOML
   :target: https://github.com/dut-media-lab/BOML
   :alt: Language

.. image:: https://img.shields.io/badge/code%20style-black-000000.svg
   :target: https://github.com/dut-media-lab/BOML
   :alt: Code style: black

BOML is a modularized optimization library that unifies several ML algorithms into a common bilevel optimization framework. It provides interfaces to implement popular bilevel optimization algorithms, so that you could quickly build your own meta learning neural network and test its performance.

**Key features of BOML**

- **Unified bilevel optimization framework** to address different categories of existing meta-learning paradigms. 
- **Modularized algorithmic structure** to integrate a variety of optimization techniques and popular methods.
- **Unit tests with Travis CI and Codecov** to reach 99% coverage, and following **PEP8 naming convention** to guarantee the code quality. 
- **Comprehensive documentations** using sphinx and **flexible functional interfaces** similar to conventional optimizers to help researchers quickly get familiar with the procedures.

**Related Links**

* `Go to the project home page <https://github.com/dut-media-lab/BOML>`_
* `Download the latest code bundle <https://codeload.github.com/dut-media-lab/BOML/zip/master>`_


