cs231n assignment(一) knn分类器
这是我自己对所学内容的总结与思考,如有错误,欢迎大家指正,若有侵权,烦请告知
一、预备知识
- KNN算法的核心思想是
1)计算已知类别中数据集的点与当前点的距离。
2)按照距离递增次序排序。
3)选取与当前点距离最小的k个点。
4)确定前k个点所在类别的出现频率。
5)返回前k个点中出现频率最高的类别作为当前点的预测分类。
- 评价两幅图像之间距离的指标:
如上图所示,L1评价指标对应的是一个菱形,菱形上的任意一点在L1上与原点等距,而L2对应的是一个圆形,圆形上的任意一点在L2上与原点等距。如果转动坐标系,将会改变点之间的L1距离,而L2距离仍然不变。因此,如果输入的特征向量、向量中的一些值对任务有一些重要的意义,那么也许L1更合适,但如果它只是空间中的一个通用向量,可能L2更好一些。
事实上,度量方式不止这两种,我们可以通过改变距离度量方式来使KNN算法适应不同的数据类型,如文本、图像等。
在本次实验中,我们使用L2欧氏距离来度量,并且用二层循环、一层循环和无循环三种方式来实现。下面我们重点看一下这部分的原理和关键代码
二层循环:直接按照公式进行
for i in range(num_test):
for j in range(num_train):
dists[i, j] = np.sqrt(np.sum((X[i, :] - self.X_train[j, :]) ** 2))
一层循环:和二层循环类似,使用numpy的广播机制同时计算一个测试数据和所有训练数据之间的距离
for i in range(num_test):
dists[i, :] = np.sqrt(np.sum(np.square(self.X_train - X[i, :]), axis=1))
numpy广播机制的原理图如下所示,想了解更多的同学可以参见[numpy广播机制]
无循环:原理图如下所示
test_sum = np.sum(np.square(X), axis=1)
train_sum = np.sum(np.square(self.X_train), axis=1)
inner_product = np.dot(X, self.X_train.T)
dists = np.sqrt(-2 * inner_product + test_sum.reshape(-1, 1) + train_sum)
- 超参数的调整
1)k设置为什么数字最有效?
2)哪种距离函数最合适?
这些都称为超参数,我们可以通过设置不同的值,来调整它的效果。
我们通常可将数据集分为三部分:训练集、验证集和测试集。
在训练集上用不同的超参来训练算法,在验证集上进行评估,然后选择一组在验证集上表现最好的超参,再在测试集上跑一跑,最后这个数据才是可以写在报告里的。
需要注意的是,我们必须将验证集和测试集分开。因为,如果没有验证集,直接在训练集上选择不同的超参,然后去测试集上跑,最后选择一组在测试集上表现最好的超参,这是不合理的,因为算法的最终目的是要应对没有见过的、全新的数据集,如果采用这种方法,选出来的超参可能只是适合这一部分测试集。 - 交叉验证
将训练集拆分为多个部分,例如这里分成了5个部分。其中4份用来训练,1份用来验证。之后循环取其中4份来训练,剩下1份做验证,取5次验证结果的平均值作为算法验证结果。最后,一旦对模型进行训练并确定了所有的最佳超参数,就可以在测试数据集上对模型进行一次评估。 - 实际上,KNN算法现在并不常用,因为它的计算量大,而且像L1、L2这样的距离度量方法实在不适合用在图像上,还有维度灾难(需要训练集密集分布)
二、实验代码
接下来,我们按照作业1的内容,用KNN算法实现对cifar10图像的分类
至此,我们完成了数据集的载入,下一步,我们需要打开 cs231n/classifiers/k_nearest_neighbor.py 完成KNN算法的核心工作
from builtins import range
from builtins import object
import numpy as np
from past.builtins import xrange
class KNearestNeighbor(object):
""" a kNN classifier with L2 distance """
def __init__(self):
pass
def train(self, X, y):
"""
Train the classifier. For k-nearest neighbors this is just
memorizing the training data.
Inputs:
- X: A numpy array of shape (num_train, D) containing the training data
consisting of num_train samples each of dimension D.
- y: A numpy array of shape (N,) containing the training labels, where
y[i] is the label for X[i].
"""
self.X_train = X
self.y_train = y
def predict(self, X, k=1, num_loops=0):
"""
Predict labels for test data using this classifier.
Inputs:
- X: A numpy array of shape (num_test, D) containing test data consisting
of num_test samples each of dimension D.
- k: The number of nearest neighbors that vote for the predicted labels.
- num_loops: Determines which implementation to use to compute distances
between training points and testing points.
Returns:
- y: A numpy array of shape (num_test,) containing predicted labels for the
test data, where y[i] is the predicted label for the test point X[i].
"""
if num_loops == 0:
dists = self.compute_distances_no_loops(X)
elif num_loops == 1:
dists = self.compute_distances_one_loop(X)
elif num_loops == 2:
dists = self.compute_distances_two_loops(X)
else:
raise ValueError('Invalid value %d for num_loops' % num_loops)
return self.predict_labels(dists, k=k)
def compute_distances_two_loops(self, X):
"""
Compute the distance between each test point in X and each training point
in self.X_train using a nested loop over both the training data and the
test data.
Inputs:
- X: A numpy array of shape (num_test, D) containing test data.
Returns:
- dists: A numpy array of shape (num_test, num_train) where dists[i, j]
is the Euclidean distance between the ith test point and the jth training
point.
"""
num_test = X.shape[0]
num_train = self.X_train.shape[0]
dists = np.zeros((num_test, num_train))
for i in range(num_test):
for j in range(num_train):
#####################################################################
# TODO: #
# Compute the l2 distance between the ith test point and the jth #
# training point, and store the result in dists[i, j]. You should #
# not use a loop over dimension, nor use np.linalg.norm(). #
#####################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
dists[i, j] = np.sqrt(np.sum((X[i, :] - self.X_train[j, :]) ** 2))
# pass
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
return dists
def compute_distances_one_loop(self, X):
"""
Compute the distance between each test point in X and each training point
in self.X_train using a single loop over the test data.
Input / Output: Same as compute_distances_two_loops
"""
num_test = X.shape[0]
num_train = self.X_train.shape[0]
dists = np.zeros((num_test, num_train))
for i in range(num_test):
#######################################################################
# TODO: #
# Compute the l2 distance between the ith test point and all training #
# points, and store the result in dists[i, :]. #
# Do not use np.linalg.norm(). #
#######################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
dists[i, :] = np.sqrt(np.sum(np.square(self.X_train - X[i, :]), axis=1))
# pass
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
return dists
def compute_distances_no_loops(self, X):
"""
Compute the distance between each test point in X and each training point
in self.X_train using no explicit loops.
Input / Output: Same as compute_distances_two_loops
"""
num_test = X.shape[0]
num_train = self.X_train.shape[0]
dists = np.zeros((num_test, num_train))
#########################################################################
# TODO: #
# Compute the l2 distance between all test points and all training #
# points without using any explicit loops, and store the result in #
# dists. #
# #
# You should implement this function using only basic array operations; #
# in particular you should not use functions from scipy, #
# nor use np.linalg.norm(). #
# #
# HINT: Try to formulate the l2 distance using matrix multiplication #
# and two broadcast sums. #
#########################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
test_sum = np.sum(np.square(X), axis=1)
train_sum = np.sum(np.square(self.X_train), axis=1)
inner_product = np.dot(X, self.X_train.T)
dists = np.sqrt(-2 * inner_product + test_sum.reshape(-1, 1) + train_sum)
#pass
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
return dists
def predict_labels(self, dists, k=1):
"""
Given a matrix of distances between test points and training points,
predict a label for each test point.
Inputs:
- dists: A numpy array of shape (num_test, num_train) where dists[i, j]
gives the distance betwen the ith test point and the jth training point.
Returns:
- y: A numpy array of shape (num_test,) containing predicted labels for the
test data, where y[i] is the predicted label for the test point X[i].
"""
num_test = dists.shape[0]
y_pred = np.zeros(num_test)
for i in range(num_test):
# A list of length k storing the labels of the k nearest neighbors to
# the ith test point.
closest_y = []
#########################################################################
# TODO: #
# Use the distance matrix to find the k nearest neighbors of the ith #
# testing point, and use self.y_train to find the labels of these #
# neighbors. Store these labels in closest_y. #
# Hint: Look up the function numpy.argsort. #
#########################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
closest_y = []
y_indicies = np.argsort(dists[i, :], axis=0)
closest_y = self.y_train[y_indicies[: k]]
y_pred[i] = np.argmax(np.bincount(closest_y))
# pass
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
#########################################################################
# TODO: #
# Now that you have found the labels of the k nearest neighbors, you #
# need to find the most common label in the list closest_y of labels. #
# Store this label in y_pred[i]. Break ties by choosing the smaller #
# label. #
#########################################################################
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
# pass
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
return y_pred
这里对比了二层循环、一层循环和无循环的执行时间,可以看出无循环的执行时间和其它两种相比非常短,所以我们应尽量减少循环,而一层循环比二层循环的时间还要长,猜想可能是广播机制中的维度扩展会花费一点时间。
从最后的结果中可以看出,准确率只有28.2%,因此在实际中很少使用该算法,但是作为一种基础性算法,也希望大家都可以很好地掌握