two loops to none loop进阶——像素矩阵处理

two loops to none loop进阶——像素矩阵处理

---

问题来源——cs231n 作业 assignment1 knn，计算 test data 与 train data 两两图片欧式距离

双层循环

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(np.square(X[i,:] - self.X_train[j,:])))
    return dists

一层循环

dists[i, :] = np.sqrt(np.sum(np.square(self.X_train - X[i, :]),axis=1))

无循环

temp_2xy = np.dot(X,self.X_train.T) * (-2)
temp_x2 = np.sum(np.square(X),axis=1,keepdims=True)
temp_y2 = np.sum(np.square(self.X_train),axis=1)
dists = temp_x2 + temp_2xy + temp_y2
dists = np.sqrt(dists)

---

原理解析——无循环（numpy矩阵运算和broadcast)

import numpy as np
#a.shape=(num,D)=(6，3)，a有6张照片，每张照片3个像素,代表train_data
#b.shape=(num,D)=(6，3)，b有6张照片，每张照片3个像素，代表test_data
a = np.array([[1,2,3],[2,3,4],[3,4,5],[4,5,6],[5,6,7],[6,7,8]])
b = np.arange(18).reshape((6,3))
ab = np.dot(a,b.T)
aa = np.sum(np.square(a),axis=1).reshape((6,1))
bb = np.sum(np.square(b),axis=1,keepdims=True)
dists =np.sqrt(aa - 2*ab  + bb)