正在学习cs231n,记录下自己写作业的过程
自己也是深度学习新手,希望能和大家多多交流学习啦,附上我的作业地址:https://github.com/donghaiyu233/cs231n,欢迎fork~。
1.knn(k-Nearest Neighbor)原理
思想:训练过程仅仅为记住所有的训练数据,predict过程为在训练数据中找与之最相近的k个图片的标签,k个标签进行一次投票,票数最高的标签即为最终的预测值。
如何计算两张图片的distance:
这是课程note中的一张图,采用L1 distance:,常用的另一个方法是L2 distance,计算两个向量间的欧式距离:,具体区别见0范数、1范数、2范数有什么区别。
2.课程作业
1)k_nearest_neighbor.py
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. #
#####################################################################
# diff = X[i,:]-self.X_train[j,:]
# diff = diff.dot(diff)
# dists[i,j]=np.sqrt(diff)
dists[i][j] = np.sqrt(np.sum(np.square(self.X_train[j,:] - X[i,:])))
#####################################################################
# END OF YOUR CODE #
#####################################################################
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, :].
#利用brodcast,将X[i,:](1*D)==>(num_train,D)
#axis=1,将每行的值加起来,结果为一个列向量
#将sum的值赋给dist[i],过程为将sum的值化为行向量再赋给左边,要求左边的列数=sum值的行数
#dists结果仍为:num_test,num_train
#######################################################################
dists[i] = np.sqrt(np.sum(np.square(X[i,:]-self.X_train),axis=1))
#######################################################################
# END OF YOUR CODE #
#######################################################################
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. #
# #
# HINT: Try to formulate the l2 distance using matrix multiplication #
# and two broadcast sums.
#X:[num_test,D], X_train:[num_train,D]
#np.dot(a,b) a*b
#np.multiply(a,b) a.*b
#########################################################################
dists = np.multiply(np.dot(X,self.X_train.T),-2)
#-2*X*X_train.T ==> [num_test,num_train]
sq1 = np.sum(np.square(X),axis=1,keepdims = True)
#np.square为对元素进行平方
#keepdims=True:如果不加,结果为列向量;如果加,则结果为[num_test,1](矩阵)
sq2 = np.sum(np.square(self.X_train),axis=1)
#结果为[num_train,1]
dists = np.add(dists,sq1)
#矩阵加也有broadcast
dists = np.add(dists,sq2)
#矩阵加一维向量,将向量转为行向量,broadcast。
dists = np.sqrt(dists)
#########################################################################
# END OF YOUR CODE #
#########################################################################
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.
#argsort返回数组从小到大的索引值,后面加上[:k]表示去索引值从头开始k个
#a=np.array([1,2,3]) a[1]=
#########################################################################
closest_y = self.y_train[np.argsort(dists[i,:])[:k]]
#########################################################################
# 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. #
#########################################################################
#np.bincount():统计次数
#example:a=np.array([1,2,3,4]) b=np.bincount(a)
# ==> b=array([0,1,1,1,1]) 统计了0-4出现的次数
#np.argmax():输出输入数组中最大元素的下标
#a = np.array([[2,4,6,1],[1,5,2,9]]) b =np.argmax(a,axis=0)
# ==> b=array([0,1,0,1])
y_pred[i] = np.argmax(np.bincount(closest_y))
#########################################################################
# END OF YOUR CODE #
#########################################################################
return y_pred
其中需要注意的是函数compute_distances_no_loops(self, X),参考MATLAB计算矩阵间的欧式距离。令测试集为P(m, d),训练集为C(n, d),m为测试数据数量,n是训练数据数量,d是维度,最后结果为下式,注意两个平方为元素的平方,最后的P*C.T为矩阵乘(点乘还是矩阵乘都可以根据矩阵的大小以及矩阵乘法的规则判断得出)。这里的实现依然利用了broadcast,P为(m, 1),C为(1, n)即可。
最后的预测部分使用np.argsort()可以对dists排序出k个最近的样本,np.bincount()统计次数,最后利用np.argmax找到出现次数最多的索引,得到预测值。
2)测试与检查验证
cross-validation,其中vstack、hstack用法
num_folds = 5
k_choices = [1, 3, 5, 8, 10, 12, 15, 20, 50, 100]
X_train_folds = []
y_train_folds = []
################################################################################
# TODO: #
# Split up the training data into folds. After splitting, X_train_folds and #
# y_train_folds should each be lists of length num_folds, where #
# y_train_folds[i] is the label vector for the points in X_train_folds[i]. #
# Hint: Look up the numpy array_split function. #
################################################################################
X_train_folds = np.split(X_train,5,axis=0)
#在行上对X_train进行五等分,即把X_train等分为5份
y_train_folds = np.split(y_train,5,axis=0)
################################################################################
# END OF YOUR CODE #
################################################################################
# A dictionary holding the accuracies for different values of k that we find
# when running cross-validation. After running cross-validation,
# k_to_accuracies[k] should be a list of length num_folds giving the different
# accuracy values that we found when using that value of k.
k_to_accuracies = {}
################################################################################
# TODO: #
# Perform k-fold cross validation to find the best value of k. For each #
# possible value of k, run the k-nearest-neighbor algorithm num_folds times, #
# where in each case you use all but one of the folds as training data and the #
# last fold as a validation set. Store the accuracies for all fold and all #
# values of k in the k_to_accuracies dictionary. #
################################################################################
for k in k_choices:
accuracies = []
for i in range(num_folds):
X_test_cv = X_train_folds[i]
X_train_cv = np.vstack(X_train_folds[:i] + X_train_folds[i+1:])
y_test_cv = y_train_folds[i]
y_train_cv = np.hstack(y_train_folds[:i]+y_train_folds[i+1:])
classifier.train(X_train_cv, y_train_cv)
dists_cv = classifier.compute_distances_no_loops(X_test_cv)
y_test_pred = classifier.predict_labels(dists_cv, k)
num_correct = np.sum(y_test_pred == y_test_cv)
accuracies.append(float(num_correct) * num_folds / num_training)
k_to_accuracies[k] = accuracies
################################################################################
# END OF YOUR CODE #
################################################################################
# Print out the computed accuracies
for k in sorted(k_to_accuracies):
for accuracy in k_to_accuracies[k]:
print('k = %d, accuracy = %f' % (k, accuracy))for k in k_choices:
accuracies = k_to_accuracies[k]
plt.scatter([k] * len(accuracies), accuracies)
# plot the trend line with error bars that correspond to standard deviation
accuracies_mean = np.array([np.mean(v) for k,v in sorted(k_to_accuracies.items())])
accuracies_std = np.array([np.std(v) for k,v in sorted(k_to_accuracies.items())])
plt.errorbar(k_choices, accuracies_mean, yerr=accuracies_std)
plt.title('Cross-validation on k')
plt.xlabel('k')
plt.ylabel('Cross-validation accuracy')
plt.show()
输出结果
k = 1, accuracy = 0.263000
k = 1, accuracy = 0.257000
k = 1, accuracy = 0.264000
k = 1, accuracy = 0.278000
k = 1, accuracy = 0.266000
k = 3, accuracy = 0.239000
k = 3, accuracy = 0.249000
k = 3, accuracy = 0.240000
k = 3, accuracy = 0.266000
k = 3, accuracy = 0.254000
k = 5, accuracy = 0.248000
k = 5, accuracy = 0.266000
k = 5, accuracy = 0.280000
k = 5, accuracy = 0.292000
k = 5, accuracy = 0.280000
k = 8, accuracy = 0.262000
k = 8, accuracy = 0.282000
k = 8, accuracy = 0.273000
k = 8, accuracy = 0.290000
k = 8, accuracy = 0.273000
k = 10, accuracy = 0.265000
k = 10, accuracy = 0.296000
k = 10, accuracy = 0.276000
k = 10, accuracy = 0.284000
k = 10, accuracy = 0.280000
k = 12, accuracy = 0.260000
k = 12, accuracy = 0.295000
k = 12, accuracy = 0.279000
k = 12, accuracy = 0.283000
k = 12, accuracy = 0.280000
k = 15, accuracy = 0.252000
k = 15, accuracy = 0.289000
k = 15, accuracy = 0.278000
k = 15, accuracy = 0.282000
k = 15, accuracy = 0.274000
k = 20, accuracy = 0.270000
k = 20, accuracy = 0.279000
k = 20, accuracy = 0.279000
k = 20, accuracy = 0.282000
k = 20, accuracy = 0.285000
k = 50, accuracy = 0.271000
k = 50, accuracy = 0.288000
k = 50, accuracy = 0.278000
k = 50, accuracy = 0.269000
k = 50, accuracy = 0.266000
k = 100, accuracy = 0.256000
k = 100, accuracy = 0.270000
k = 100, accuracy = 0.263000
k = 100, accuracy = 0.256000
k = 100, accuracy = 0.263000
best_k = 10