CS231n assignment1 KNN

时间：2019/3/25
内容：assignment1-KNN

参考网上大佬的代码。还是计算机视觉小白，有错误欢迎指正~

https://blog.csdn.net/donghai_yu/article/details/79344539
https://blog.csdn.net/qq_26414307/article/details/79318555

KNN部分

完整代码

import numpy as np

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.                                    #
        #####################################################################
      
        dists[i,j]=np.sqrt(np.sum((X[i,:]-self.X_train[j,:])**2))

        #####################################################################
        #                       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, :].                        #
      #######################################################################
    
      dists[i,:]=np.sqrt(np.sum(np.square(self.X_train-X[i,:]),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.                                         #
    #########################################################################
    dists = np.multiply(np.dot(X,self.X_train.T),-2) 
    sq1 = np.sum(np.square(X),axis=1,keepdims = True) 
    sq2 = np.sum(np.square(self.X_train),axis=1) 
    dists = np.add(dists,sq1) 
    dists = np.add(dists,sq2)
    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.                             #
      #########################################################################
      y_indicies=np.argsort(dists[i,:],axis=0)
      #########################################################################
      # 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.                                                                #
      #########################################################################
      
      closest_y=self.y_train[y_indicies[: k]]   
      y_pred[i]=np.argmax(np.bincount(closest_y))

      #########################################################################
      #                           END OF YOUR CODE                            # 
      #########################################################################

    return y_pred
    

代码理解

习题中使用了三种方法来计算L2，首先是用两个循环实现：

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]   # 读取X的第一维长度，X的第一维即num_test（见上面注释）
    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.                                    #
        #####################################################################
        
        # [i,:]数组切片，是取第1维中下标为i的元素的所有数据，也就是第i行全部元素（从0开始），此处表示第i个样本点          
        # KNN算法需要计算测试集的点与训练集所有点的距离，也就是训练集与测试集两两点求距离
        # L2是欧氏距离（所有点差的平方之和，再开根号）
        dists[i,j]=np.sqrt(np.sum((X[i,:]-self.X_train[j,:])**2))

        #####################################################################
        #                       END OF YOUR CODE                            #
        #####################################################################
    return dists

然后用一个循环实现：

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
    """
    # 以下三行与两个循环的一样
    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, :].                        #
      #######################################################################
     
      # axis=1是按行相加
      # numpy的broadcast
      dists[i,:]=np.sqrt(np.sum(np.square(self.X_train-X[i,:]),axis=1))

      #######################################################################
      #                         END OF YOUR CODE                            #
      #######################################################################
    return dists

不用循环实现：

 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.                                         #
    #########################################################################
    # 思想：(a-b)^2 = a^2 + b^2 -2ab
    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

补充关于nump.square的用法：

对于矩阵做平方，结果矩阵和输入的shape相同，结果中的每一个元素是原来位置元素的平方

numpy库中的reshape(-1,1)中-1被理解为unspecified value，意思是未指定为给定的。因此reshape(-1,1)变成1列，同理reshape(1,-1)会变成1行
可以参考： https://blog.csdn.net/wld914674505/article/details/80460042

预测部分:

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]  # 表示dist的行数
    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返回数组中值（此处是距离）从小到大的索引值
      # [i,:]表示第i行的所有元素
 	  # 主要y_indicies中都是一些索引值
      # 由于dists形状是(num_test,num_train)，因此每行最前面的是训练集中距离该测试点最近的
      y_indicies=np.argsort(dists[i,:],axis=0)
      
      #########################################################################
      # 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.                                                                #
      #########################################################################
      
      # [: k]表示从开始到k
      # argmax返回最大值（此处为次数最大值）对应的索引值；具体分类也是用具体数字表示的所以不会有问题
      closest_y=self.y_train[y_indicies[: k]]   # 距离最近的训练集前k个点的label
      y_pred[i]=np.argmax(np.bincount(closest_y))

      #########################################################################
      #                           END OF YOUR CODE                            # 
      #########################################################################

    return y_pred

补充：np.bincount的用法

交叉验证部分

完整代码

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.                                #
################################################################################
# Your code
y_train_ = y_train.reshape(-1, 1)
X_train_folds = np.array_split(X_train, num_folds)
y_train_folds = np.array_split(y_train, num_folds)

################################################################################
#                                 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.                               #
################################################################################
# Your code
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))

代码理解

y_train_ = y_train.reshape(-1, 1)
X_train_folds = np.array_split(X_train, num_folds)
y_train_folds = np.array_split(y_train, num_folds)

for k in k_choices:
    accuracies = []
    for i in range(num_folds):
        X_test_cv = X_train_folds[i]
        # 具体这样拼接的原因要根据data的形状分析
        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