diff --git a/knn.py b/knn.py
index 0be4178eaf8d12e447b0e66e298ccff85b04f52b..1fd7fa48ac3bf08a5583b63d19aa2920f107c265 100644
--- a/knn.py
+++ b/knn.py
@@ -8,49 +8,65 @@ import read_cifar
import numpy as np
import statistics
from statistics import mode
+import time
+import matplotlib.pyplot as plt
def distance_matrix(A,B) :
- # sum_of_squaresA = np.sum(A ** 2, axis=1)
- # sum_of_squaresB = np.sum(B ** 2, axis=1)
- sum_of_squaresA = np.sum(np.square(A), axis=1)
- sum_of_squaresB = np.sum(np.square(B) ** 2, axis=1)
-
+ 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.dot(A, B.T)
-
+ # dot_product = np.matmul(A, B.T)
+ dot_product = np.einsum('ij,jk', A, B.T)
+ print("test2")
# 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_test, number_train = dists.shape
+ number_train, number_test = dists.shape
# initialze the predicted labels to zeros
labels_predicted = np.zeros(number_test)
- for i in range(number_test) :
- sorted_indices = np.argsort(dists[i])
+ 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[i] = label_predicted
+ labels_predicted[j] = label_predicted
return labels_predicted
def evaluate_knn(data_train, labels_train, data_test, labels_test, k) :
- dists = distance_matrix(data_test, data_train)
+ 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]
classification_rate = number_true_prediction/number_total_prediction
return classification_rate
+
+def plot_accuracy(data_train, labels_train, data_test, labels_test, k_max) :
+ Y = []
+ for k in range(1, k_max+1) :
+ Y += [evaluate_knn(data_train, labels_train, data_test, labels_test, k)]
+ plt.plot(list(range(1, k_max+1)), Y)
+ plt.xlabel('k (Number of Neighbors)')
+ plt.ylabel('Accuracy')
+ plt.savefig('results/knn.png')
+
if __name__ == "__main__" :
-
+ t1 = time.time()
# # Example distance matrix, training labels, and k value
# dists = np.array([[1000, 2, 3],
# [4, 0.1, 6],
@@ -62,14 +78,23 @@ if __name__ == "__main__" :
# 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, 0.8)
+ # 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)
- # k = 2
- # knn_predict(dists, labels_train, k)
\ No newline at end of file
+ # 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
diff --git a/mlp.py b/mlp.py
new file mode 100644
index 0000000000000000000000000000000000000000..825ce394b75b7307eeeace901b920186255b6d9c
--- /dev/null
+++ b/mlp.py
@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Oct 27 16:48:16 2023
+
+@author: oscar
+"""
+
+import numpy as np
+
+
+def learn_once_mse(w1, b1, w2, b2, data, targets, learning_rate) :
+ a0 = data # the data are the input of the first layer
+ z1 = np.matmul(a0, w1) + b1 # input of the hidden layer
+ a1 = 1 / (1 + np.exp(-z1)) # output of the hidden layer (sigmoid activation function)
+ z2 = np.matmul(a1, w2) + b2 # input of the output layer
+ a2 = 1 / (1 + np.exp(-z2)) # output of the output layer (sigmoid activation function)
+ predictions = a2 # the predicted values are the outputs of the output layer
+ N = targets.shape[0]
+
+ # calculation of partial derivates of C
+ dCdA2 = 2/N * (a2 - targets)
+ dCdZ2 = dCdA2 * (a2 - a2**2)
+ dCdW2 = np.matmul(a1.T, dCdZ2)
+ dCdB2 = (1/N) * np.sum(dCdZ2, axis=0, keepdims=True)
+ dCdA1 = np.matmul(dCdZ2, w2.T)
+ dCdZ1 = dCdA1 * (a1 - a1**2)
+ dCdW1 = np.matmul(a0.T, dCdZ1)
+ dCdB1 = (1/N) * np.sum(dCdZ1, axis=0, keepdims=True)
+
+ # one gradient descent step
+ w1 -= dCdW1 * learning_rate
+ b1 -= dCdB1 * learning_rate
+ w2 -= dCdW2 * learning_rate
+ b2 -= dCdB2 * learning_rate
+
+ loss = np.mean(np.square(predictions - targets))
+
+ return w1, b1, w2, b2, loss
+
+
\ No newline at end of file
diff --git a/read_cifar.py b/read_cifar.py
index 6d5369d0cb4811936d948940ff6bd82e1f671615..f25324d500f4cdcb148bd6dcb38f9b482cbe749e 100644
--- a/read_cifar.py
+++ b/read_cifar.py
@@ -24,24 +24,41 @@ def read_cifar (batch_dir) :
data_batches = []
label_batches = []
- for i in range(1,6) :
+ for i in range(1,4) :
batch_filename = f'data_batch_{i}'
batch_path = os.path.join(batch_dir, batch_filename)
data, labels = read_cifar_batch(batch_path)
data_batches.append(data)
label_batches.append(labels)
- test_batch_filename = 'test_batch'
- test_batch_path = os.path.join(batch_dir, test_batch_filename)
- data_test, labels_test = read_cifar_batch(test_batch_path)
- data_batches.append(data_test)
- label_batches.append(labels_test)
+ # test_batch_filename = 'test_batch'
+ # test_batch_path = os.path.join(batch_dir, test_batch_filename)
+ # data_test, labels_test = read_cifar_batch(test_batch_path)
+ # data_batches.append(data_test)
+ # label_batches.append(labels_test)
data = np.concatenate(data_batches, axis=0)
labels = np.concatenate(label_batches, axis=0)
return data, labels
+# def read_cifar(directory_path):
+# batches = os.listdir(directory_path)
+# data=None
+# labels=None
+
+# for batch in batches:
+# batch_path = os.path.join(directory_path, batch)
+# if not batch_path.endswith(".meta"):
+# data_batch,labels_batch=read_cifar_batch(batch_path)
+# if data is None:
+# data=data_batch
+# labels=labels_batch
+# else:
+# data=np.concatenate((data,data_batch))
+# labels=np.concatenate((labels,labels_batch))
+# return(data, labels)
+
def split_dataset(data, labels, split) :
number_total = data.shape[0]
diff --git a/results/knn.png b/results/knn.png
new file mode 100644
index 0000000000000000000000000000000000000000..393d194fbe612e40cf83ef7dd8f14d34f3fc698b
Binary files /dev/null and b/results/knn.png differ
diff --git a/test1.py b/test1.py
new file mode 100644
index 0000000000000000000000000000000000000000..5bc93fb8ee1dd43c732eb6da06ce8dc62c77586b
--- /dev/null
+++ b/test1.py
@@ -0,0 +1,52 @@
+# -*- 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