diff --git a/README.md b/README.md
index c7d2a292450fa11009dc8c22cf2a9cd78e688d78..4a2028e42c50696c5d04edebebeff33daca6dd73 100644
--- a/README.md
+++ b/README.md
@@ -1,14 +1,33 @@
# Image Classification
Ce projet de Classification d'image a été réalisé dans le cadre du cours d'Apprentissage Profond et Intelligence Artificielle de l'Ecole Centrale Lyon.
-Le but du projet est de développer grâce à diférentes méthodes des algorithmes de machone learning pour la classification d'images.
+Le but du projet est de développer grâce à diférents algorithmes de machine learning pour la classification d'images.
## Introduction
Deux algorithmes de classification d'images sont développés dans ce projet :
- k-nearest neighbors
-- Artificial Neural Network
+- Artificial Neural Network (réseau de neurones artificels)
+
+## Installation
+
+Ce projet nécessite Python3 ainsi que les librairies suivantes :
+- Numpy
+- Pickle
+- Matplotlib
+
## Dataset
La base de données CIFAR-10 est utilisée dans ce projet pour entrainer et tester les algorithmes de classification. Cette base de données peut être trouvée a l'adresse suivante : https://www.cs.toronto.edu/~kriz/cifar.html.
+
+## Structure du projet
+
+Le projet est divisé en trois sections ayant chacune un script distinct :
+- lecture et préparation du dataset (code read_cifar.py)
+- algorithme k-nearest neighbors (code knn.py)
+- algorithme de réseau de neurones artificiels (code mlp.py)
+
+## Auteur
+Oscar CHAUFOUR
+
diff --git a/knn.py b/knn.py
index 4dc7d61363961d8093d446d6df5ff8eca607d050..f3006bde1c5699e67ce407b33bb71d85af6da9df 100644
--- a/knn.py
+++ b/knn.py
@@ -10,80 +10,59 @@ import statistics
from statistics import mode
import time
import matplotlib.pyplot as plt
+from tqdm import tqdm
def distance_matrix(A,B) :
- print("test0")
sum_of_squaresA= np.sum(A**2, axis = 1, keepdims = True)
sum_of_squaresB = np.sum(B**2, axis = 1)
- print("test1")
# sum_of_squaresA = np.tile(sum_of_squaresAVect, (np.shape(B)[0], 1))
# sum_of_squaresB = np.tile(sum_of_squaresBVect, (np.shape(A)[0], 1))
# Calculate the dot product between the two matrices
- # dot_product = np.matmul(A, B.T)
- dot_product = np.einsum('ij,jk', A, B.T)
- print("test2")
+ dot_product = np.dot(A, B.T)
+ # dot_product = np.einsum('ij,jk', A, B.T)
# Calculate the Euclidean distance matrix using the hint provided
dists = np.sqrt(sum_of_squaresA + sum_of_squaresB - 2 * dot_product)
- print("test3")
return dists
def knn_predict(dists, labels_train, k) :
- number_train, number_test = dists.shape
+ number_train, number_test = np.shape(dists)
# initialze the predicted labels to zeros
labels_predicted = np.zeros(number_test)
for j in range(number_test) :
sorted_indices = np.argsort(dists[:, j])
- print(len(dists[:, j]))
- break
knn_indices = sorted_indices[ : k]
knn_labels = labels_train[knn_indices]
label_predicted = mode(knn_labels)
labels_predicted[j] = label_predicted
-
return labels_predicted
def evaluate_knn(data_train, labels_train, data_test, labels_test, k) :
dists = distance_matrix(data_train, data_test)
labels_predicted = knn_predict(dists, labels_train, k)
number_true_prediction = np.sum(labels_test == labels_predicted)
- number_total_prediction = labels_test.shape[0]
+ number_total_prediction = len(labels_test)
classification_rate = number_true_prediction/number_total_prediction
-
+ print(classification_rate)
return classification_rate
if __name__ == "__main__" :
- t1 = time.time()
- # # Example distance matrix, training labels, and k value
- # dists = np.array([[1000, 2, 3],
- # [4, 0.1, 6],
- # [7, 8, 0]])
- # labels_train = np.array([0, 1, 5])
- # k = 2
-
- # # Predict labels for the test set using k-NN
- # predicted_labels = knn_predict(dists, labels_train, k)
-
-
- # classification_rate = evaluate_knn(np.array([[1, 27], [100, 300]]), np.array([0.002, 9000]), np.array([[25, 350]]), np.array([9000]), 1)
- # print("Classification rate:")
- # print(classification_rate)
-
file = "./data/cifar-10-python/"
data, labels = read_cifar.read_cifar(file)
data_train, labels_train, data_test, labels_test = read_cifar.split_dataset(data, labels, 0.9)
- k = 10
- print(len(data_train))
- print(len(data_test))
- print(len(data_train[0]))
- print(len(data_test[0]))
- # dists = distance_matrix(data_train, data_test)
- # knn_predict(dists, labels_train, k)
- classification_rate = evaluate_knn(data_train, labels_train, data_test, labels_test, k)
- print("classification rate :", classification_rate)
- # plot_accuracy(data_train, labels_train, data_test, labels_test, 4)
- t2 = time.time()
- print('run time (second): ')
- print(t2-t1)
\ No newline at end of file
+
+ k = 8
+ evaluations = []
+ for k in tqdm(range(1, k)) :
+ evaluations.append(evaluate_knn(data_train, labels_train, data_test, labels_test, k))
+
+ fig=plt.figure()
+ plt.title("Prediction accuracy as a function of k")
+ plt.xlabel("k-nearest neighbors")
+ plt.ylabel("Accuracy (%)")
+ plt.plot(evaluations)
+ plt.show()
+ plt.savefig('results/knn.png')
+
diff --git a/test1.py b/test1.py
deleted file mode 100644
index 5bc93fb8ee1dd43c732eb6da06ce8dc62c77586b..0000000000000000000000000000000000000000
--- a/test1.py
+++ /dev/null
@@ -1,52 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-Created on Mon Oct 23 19:43:47 2023
-
-@author: oscar
-"""
-
-import numpy as np
-from collections import Counter
-import read_cifar
-
-def distance_matrix(M1,M2):
- # dists(i,j) = dist entre ième ligne de M1 et jème ligne de M1, soit la racine de sum((M1i,p - M2j,p)²))
- # qu'on peut simplifier en sum(M1i,p²) + sum(M2j,p²) - sum(2* M1j,p * M2i,p)
-
- l1=np.shape(M1)[0]
- l2=np.shape(M2)[0]
- Vect1=np.sum(M1**2,1)
- Vect2=np.sum(M2**2,1)
-
- Mat1=np.tile(Vect1, (l2,1))
- Mat2=np.tile(Vect2, (l1,1))
- Mat3=2*np.dot(M1,M2.T)
-
- dists=np.sqrt(Mat1.T+Mat2-Mat3)
-
- return dists
-
-def knn_predict(dists,labels_train,k):
- labels_predict=np.array([])
- size_test=np.shape(dists)[1]
- for j in range(size_test):
- list_arg_min=np.argsort(dists[:,j])
- labels_sorted=[labels_train[i] for i in list_arg_min]
- k_labels=labels_sorted[:k]
- count = Counter(k_labels)
-
- labels_predict=np.append(labels_predict,count.most_common(1)[0][0])
-
- return labels_predict
-
-def evaluate_knn(data_train,data_test,labels_train,labels_test,k):
- dists=distance_matrix(data_train,data_test)
- labels_predict=knn_predict(dists,labels_train,k)
- count=np.sum(labels_predict==labels_test)
- return count/np.shape(labels_predict)
-
-if __name__ == "__main__":
- file = "./data/cifar-10-python/"
- data, labels = read_cifar.read_cifar(file)
- data_train,labels_train,data_test,labels_test=read_cifar.split_dataset(data,labels,0.9)
- print(evaluate_knn(data_train,data_test,labels_train,labels_test,20))
\ No newline at end of file