ahmedfgad/GeneticAlgorithmPython

Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).

What it solves

PyGAD is a library designed to simplify the implementation of genetic algorithms (GAs) for optimization problems. It allows users to find optimal parameters or solutions for a given fitness function, which is useful for optimizing machine learning algorithms, including those built with Keras and PyTorch.

How it works

The library provides a pygad.GA class that manages the population of potential solutions. Users define a fitness function that evaluates how well a solution performs. PyGAD then evolves the population through generations using various types of crossover, mutation, and parent selection methods to iteratively improve the fitness of the solutions.

Who it’s for

It is intended for developers and data scientists who need to perform optimization tasks, specifically those looking to integrate genetic algorithms into their Python-based machine learning workflows.

Highlights

  • Supports both single-objective and multi-objective optimization problems.
  • Integration with Keras and PyTorch for optimizing deep learning models.
  • Flexible configuration of crossover, mutation, and selection methods.
  • Includes plotting features to visualize fitness evolution over generations.
  • Ability to save and load GA instances to resume optimization processes.

Related

  • Project
    pypose/bae

    A PyTorch‑based library that provides exact second‑order (Levenberg‑Marquardt, Schur‑complement) optimizers for sparse robotics problems such as Bundle Adjustment and Pose‑Graph Optimization, with CUDA acceleration, PyPose integration, and support for torch.compile.

  • Project
    NVIDIA/cuEquivariance

    An NVIDIA Python library for building high-performance geometric neural networks that respect 3D symmetries using optimized CUDA kernels and segmented polynomials.

  • Project
    kozistr/pytorch_optimizer

    A PyTorch‑compatible library that aggregates 100+ research optimizers, several LR schedulers and loss functions behind a single, consistent API, with optional integrations for low‑precision training.

  • Project
    pytorch/pytorch

    A Python-based machine learning framework that provides GPU-accelerated tensor computation and a dynamic autograd system for building deep neural networks.

  • Project
    nnaisense/evotorch

    A scalable evolutionary computation library built on PyTorch that solves non-differentiable optimization problems using GPU acceleration and Ray distribution.