@@ -4,9 +4,20 @@ BE1: MOD 4.6 Deep Learning & Artificial Intelligence: an introduction
## Introduction
To make it easy for you to get started with GitLab, here's a list of recommended next steps.
This project includes image classification and uses the cifar10 dataset. Its objectives are: to write a complete image classification program in Python.
Two classification models are developed: first, the k-nearest neighbors (KNN) and then the neural networks (NN).
The project is divided into three main parts:
- The data importation (read_cifar.py), where we write functions to import the cifar10 dataset and split it into training and testing sets.
- KNN, in this part we develop the knn program and test it to compare the evolution of the accuracy depending on the number of neighbors k. (the corresponding result is named accuracy_knn and is imported in the file 'results').
- Mlp, this final part concerns the neural networks program and it also contains the comparison of the accuracy depending on the number of epoches.
Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
## data
The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.
The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.
The classes are : [airplane,automobile,bird,cat,deer,dog,frog,horse,ship,truck]
