Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found
Select Git revision
  • main
1 result

Target

Select target project
No results found
Select Git revision
  • main
1 result
Show changes

Commits on Source 4

4 files
+ 15
− 7
Compare changes
  • Side-by-side
  • Inline

Files

knn.py

+5 −1
Original line number Original line Diff line number Diff line 
#Libraries

#Libraries

import numpy as np

import numpy as np

import matplotlib.pyplot as plt

import matplotlib.pyplot as plt

import math

import random

from read_cifar import *



#Functions

#Functions

def distance_matrix(Y , X):

def distance_matrix(Y , X):

    #This function takes as parameters two matrices X and Y

    #This function takes as parameters two matrices X and Y
@@ -26,7 +30,7 @@ def knn_predict(dists, labels_train, k): 




def evaluate_knn(data_train, labels_train, data_test, labels_test, k):

def evaluate_knn(data_train, labels_train, data_test, labels_test, k):

    #This function evaluates the knn classifier rate

    #This function evaluates the knn classifier rate

    labels_test__pred=knn_predict(distance_matrix(data_train, data_test), labels_train, k)

    labels_test_pred=knn_predict(distance_matrix(data_train, data_test), labels_train, k)

    num_samples= data_test.shape[0]

    num_samples= data_test.shape[0]

    num_correct= (labels_test == labels_test_pred).sum().item()

    num_correct= (labels_test == labels_test_pred).sum().item()

    accuracy= 100 * (num_correct / num_samples)  #The accuracy is the percentage of the correctly predicted classes

    accuracy= 100 * (num_correct / num_samples)  #The accuracy is the percentage of the correctly predicted classes

mlp.py

+5 −1
Original line number Original line Diff line number Diff line 
import numpy as np

import numpy as np

import matplotlib.pyplot as plt

import math

import random

from read_cifar import *

#We are using the segmoid activation function

#We are using the segmoid activation function

def segmoid(x):

def segmoid(x):

    return 1/(1+np.exp(-x))

    return 1/(1+np.exp(-x))
@@ -19,7 +23,7 @@ def learn_once_mse(w1,b1,w2,b2,data,targets,learning_rate): 
    A2=segmoid(np.matmul(A1,w2) + b2)

    A2=segmoid(np.matmul(A1,w2) + b2)

    #Let calculate the partial derivates

    #Let calculate the partial derivates

    #2

    #2

    D_A2=2*(A2-tragets)

    D_A2=2*(A2-targets)

    D_A2_T=np.matmul(A2,(1-A2).T)

    D_A2_T=np.matmul(A2,(1-A2).T)

    D_Z2=np.matmul(D_A2_T,D_A2)

    D_Z2=np.matmul(D_A2_T,D_A2)

    D_W2=np.matmul(A1.T,D_Z2)

    D_W2=np.matmul(A1.T,D_Z2)

read_cifar.py

+5 −5
Original line number Original line Diff line number Diff line
@@ -29,13 +29,13 @@ def read_cifar(directory_path): 
    for i in range(len(files)):

    for i in range(len(files)):

        fichier=directory_path+files[i]

        fichier=directory_path+files[i]

        data_dict=unpickle(fichier)

        data_dict=unpickle(fichier)

        M=data_dict[b'data']

        D=data_dict[b'data']

        L=data_dict[b'labels']

        L=data_dict[b'labels']

        L=np.array(L)

        L=np.array(L)

        data=np.vstack((X,M))

        data=np.vstack((data,D))

        labels=np.hstack((Y,L))

        labels=np.hstack((labels,L))

    data=X[N:2*N,]

    data=data[N:2*N,]

    labels=Y[A:,]

    labels=labels[A:,]

    return data,labels

    return data,labels





def split_dataset(data,labels,split):

def split_dataset(data,labels,split):