Skip to content
Snippets Groups Projects
Select Git revision
  • 16cd405175fe3b6d5d9c8158dcaf30b1a0d8744c
  • main default protected
2 results

image-classification

Danjou Pierre's avatar
Delete mlp.png
Danjou Pierre authored 
bcs not in the good file
16cd4051
History
Danjou Pierre's avatar 16cd4051
History
Name Last commit Last update
data/cifar-10-batches-py
results
.gitignore
README.md
knn.py
mlp.py
read_cifar.py
README.md

TD1 - Image classification - DANJOU Pierre

INTRODUCTION

The objective of this tutorial is to write a complete image classification program in Python. Two classification models will be successively developed and tested: k-nearest neighbors (KNN) and neural networks (NN).

Prepare the CIFAR dataset

First of all, we had to prepare the CIFAR dataset. All the code can be found on the python file read_cifar.py

K-Nearest Neighbors (KNN)

All the code can be found on the python file knn.py

Here is the graph of the accuracy of my knn code epending on the value of k for the Cifar dataset with a split factor of 0.9: knn

Here we can conclude that the best K is 5, (if we don't use k = 1) with a performace of 34,5% of accuracy.

Artificial Neural Network

Maths

1°

​

Code