Skip to content
Snippets Groups Projects
Select Git revision
  • main default protected
1 result

README.md

Blame
  • README.md 1.02 KiB

    Introduction

    This tutorial aims to create a comprehensive Python program for image classification. It involves the development and testing of two classification models: k-nearest neighbors (KNN) and neural networks (NN). The experimentation will be conducted using the CIFAR-10 image database, which comprises 60,000 color images of dimensions 32x32 distributed across 10 classes (e.g., plane, car, bird, cat, ...).

    To access the CIFAR-10 database and obtain the necessary data, you can visit https://www.cs.toronto.edu/~kriz/cifar.html, where instructions on data retrieval are provided. Consequently, the project is structured into three files:

    • read_cifar
    • knn
    • mlp

    KNN

    The result obtained from the k-nearest neighbors (KNN) is presented as the accuracy, showcasing how it varies with changes in the value of k, ranging from 1 to 20.

    Description de l'image

    NN

    The output from the neural networks (NN) illustrates the progression of learning accuracy over different learning epochs.