Code Monkey home page Code Monkey logo

class_imbalance_inside_cnns's Introduction

A Study on the Effectiveness of the Class Imbalance of Training Data on Convolutional Networks(CNNs)

Experiment about class imbalance problems inside the CNNs

Prerequistes

  1. pytorch, python : pytorch 1.0 ↑, python 3.7 ↑
  2. package : numpy, os

Measures Definition

  1. Neuron Membership
 2. Major class actvation - Minor class activation 3. Class Selectivity

Dataset / Model

  1. Data : Cifar10 with different imbalance ratio
Dataset Cifar10
Major / Minor Major class images per group Minor class images per group Accuracy
Balanced [0~4] / [5~9] 5000 5000 91.29
Imbalance 20 250 68.93
Imbalance 50 100 58.51
Imbalance 100 50 52.45
  1. Model : Vgg11 with batch normalization

Experiment Result

  1. Neuron Membership
  1. Major class actvation - Minor class activation
  1. Class Selectivity

class_imbalance_inside_cnns's People

Contributors

hongchunchoi avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.