From 72bb7ee1d99b7365de5ee90770132b7a6b5fb9ae Mon Sep 17 00:00:00 2001
From: lucile <lucile.audard@ecl20.ec-lyon.fr>
Date: Tue, 7 Nov 2023 13:53:01 +0100
Subject: [PATCH] Update knn.py
---
knn.py | 48 +++++++++++++++++++++++++++++++++++-------------
1 file changed, 35 insertions(+), 13 deletions(-)
diff --git a/knn.py b/knn.py
index 54a3d58..2e11742 100644
--- a/knn.py
+++ b/knn.py
@@ -1,15 +1,20 @@
import numpy as np
+from read_cifar import *
+import matplotlib.pyplot as plt
def distance_matrix(mat1, mat2):
- square1 = np.sum(np.square(mat1), axis = 1)
- square2 = np.sum(np.square(mat2), axis = 1)
+ # A^2 and B^2
+ square1 = np.sum(np.square(mat1), axis = 1, keepdims=True)
+ square2 = np.sum(np.square(mat2), axis = 1, keepdims=True)
+ # A*B
prod = np.dot(mat1, mat2.T)
- dists = np.sqrt(square1 + square2 - 2 * prod)
+ # A^2 + B^2 -2*A*B
+ dists = np.sqrt(square1 + square2.T - 2 * prod)
return dists
def knn_predict(dists, labels_train, k):
- # results matrix initialisation
+ # results matrix initialization
predicted_labels = np.zeros(len(dists))
# loop on all the test images
for i in range(len(dists)):
@@ -19,17 +24,21 @@ def knn_predict(dists, labels_train, k):
# get the matching labels_train
closest_labels = labels_train[k_sorted_dists]
# get the most common labels_train
- predicted_labels[i] = np.argmax(closest_labels)
+ uniques, counts = np.unique(closest_labels, return_counts = True)
+ predicted_labels[i] = uniques[np.argmax(counts)]
return np.array(predicted_labels)
def evaluate_knn(data_train, labels_train, data_test, labels_test, k):
dists = distance_matrix(data_test, data_train)
+ # Determine the number of images in data_test
tot = len(data_test)
accurate = 0
predicted_labels = knn_predict(dists, labels_train, k)
+ # Count the number of images in data_test whose label has been estimated correctly
for i in range(tot):
if predicted_labels[i] == labels_test[i]:
accurate += 1
+ # Calculate the classification rate
accuracy = accurate/tot
return accuracy
@@ -42,14 +51,27 @@ def evaluate_knn(data_train, labels_train, data_test, labels_test, k):
if __name__ == "__main__":
- bench_knn()
- # data, labels = read_cifar.read_cifar('image-classification/data/cifar-10-batches-py')
- # X_train, X_test, y_train, y_test = read_cifar.split_dataset(data, labels, 0.9)
- # print(evaluate_knn(X_train, y_train, X_test, y_test, 5))
- # print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)
+ data, labels = read_cifar("./data/cifar-10-batches-py")
+ data_train, labels_train, data_test, labels_test = split_dataset(data, labels, 0.9)
+
+ k_list = [k for k in range(1, 21)]
+ accuracy = [evaluate_knn(data_train, labels_train, data_test, labels_test, k) for k in range (1, 21)]
+
+ plt.plot([k for k in range (1, 21)], accuracy)
+ plt.title("Variation of k-nearest neighbors method accuracy for k from 1 to 20")
+ plt.xlabel("k value")
+ plt.ylabel("Accuracy")
+ plt.grid(True, which='both')
+ plt.savefig("results/knn.png")
+
- # y_test = []
# x_test = np.array([[1,2],[4,6]])
+ # x_labels_test = np.array([0,1])
# x_train = np.array([[2,4],[7,2],[4,6]])
- # y_train = [1,2,1]
- # dist = distance_matrix(x_test,x_train)
+ # x_labels_train = np.array([0,1,1])
+
+ # dist = distance_matrix(x_test, x_train)
+ # accuracy = evaluate_knn(x_train, x_labels_train, x_test, x_labels_test, 1)
+ # print(accuracy)
+
+
--
GitLab