Skip to content

Paper "Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization" Program

License

Notifications You must be signed in to change notification settings

ta-seri/LDWPSO-CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 

Repository files navigation

LDWPSO CNN

Python implementation of LDWPSO CNN (Linearly Decreasing Particle Swarm Optimization Convolutional Neural Network).
The program rewrites and uses part of the Hyperactive library.

Article: Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization

Usage

Requirement

  • Python 3.8
  • scikit leran 1.0
  • keras 2.8

LDWPSO CNN

  1. Clone this repository

  2. The baseline LeNet-5 can be run with the following command

    python src/lenet5.py
    
  3. If you use MNIST dataset, you can use the following command.

    python src/pso_mnist.py
    
  4. If you use CIFAR-10 dataset, you can use the following command.

    python src/pso_cifar10.py
    

Validation

The output parameters can be verified by rewriting the following program.

  • src/pso_mnist_result.py
  • src/pso_cifar10_result.py

Use data

  • MNIST
  • CIFAR-10

About

Paper "Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization" Program

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published