深度学习（一）

写在前面：使用Python的一些小问题
查看Python安装路径方法：使用命令py -0p

1. 矢量化

import time

import numpy as np

x1 = [9, 2, 5, 0, 0, 7, 5, 0, 0, 0, 9, 2, 5, 0, 0]
x2 = [9, 2, 2, 9, 0, 9, 2, 5, 0, 0, 9, 2, 5, 0, 0]


tic = time.process_time()

 ###矩阵乘法 如果是向量相乘 结果是内奇数；矩阵相乘结果按照矩阵乘法计算
dot = np.dot(x1,x2)   

toc = time.process_time()


print("dot = " + str(dot) +"\n ----- Computation time = " + str(1000*(toc - tic)) + "ms")


tic = time.process_time()


###计算向量的外积
outer = np.outer(x1,x2)
toc = time.process_time()
print ("outer = " + str(outer) + "\n ----- Computation time = " + str(1000*(toc - tic)) + "ms")

2. L1 和 L2 损失函数

L1损失函数：

import numpy as np

def L1(yhat,y):

    loss = np.sum(np.abs(y-yhat))
    return loss
yhat = np.array([.9, 0.2, 0.1, .4, .9])
y = np.array([1, 0, 0, 1, 1])
print("L1 = " + str(L1(yhat,y)))

L2损失函数：

import numpy as np

def L2(yhat,y):

    ###numpy.power()用于数组元素求n次方求和
    loss = np.sum(np.power((y-yhat),2))
    return loss
yhat = np.array([.9, 0.2, 0.1, .4, .9])
y = np.array([1, 0, 0, 1, 1])
print("L2 = " + str(L2(yhat,y)))

3. python中的zero用法

用法：zeros(shape, dtype=float, order=‘C’)

返回：返回来一个给定形状和类型的用0填充的数组；

4.初始化参数

import numpy as np
import matplotlib.pyplot as plt
import h5py 
import scipy


def initialize_with_zeros(dim):

    w = np.zeros((dim,1))
    b = 0

    
    ### 为真的时候运行
    assert(w.shape == (dim,1))
    assert(isinstance(b, float) or isinstance(b, int))
    
    return w, b


dim = 2
w, b = initialize_with_zeros(dim)
print ("w = " + str(w))
print ("b = " + str(b))

5.正向传播

import numpy as np
import matplotlib.pyplot as plt
import h5py 
import scipy

def sigmoid(z):
    """
    Compute the sigmoid of z

    Arguments:
    z -- A scalar or numpy array of any size.

    Return:
    s -- sigmoid(z)
    """

    ### START CODE HERE ### (≈ 1 line of code)
    s = 1.0/(1+np.exp(-z))
    ### END CODE HERE ###
    
    return s

def propagate(w,b,X,Y):

    m = X.shape[1]
    ###表示矩阵的转置
    A = sigmoid(np.dot(w.T,X)+b)

    cost = -(1.0/m)*np.sum(Y*np.log(A)+(1-Y)*np.log(1-A))         


    dw = (1.0/m)*np.dot(X,(A-Y).T)
    db = (1.0/m)*np.sum(A-Y)
    assert(dw.shape == w.shape)
    assert(db.dtype == float)

    # 从数组的形状中删除单维条目，即把shape中为1的维度去掉
    cost = np.squeeze(cost)
    assert(cost.shape == ())
    
    grads = {"dw": dw,
             "db": db}
    
    return grads, cost


w, b, X, Y = np.array([[1.],[2.]]), 2., np.array([[1.,2.,-1.],[3.,4.,-3.2]]), np.array([[1,0,1]])
grads, cost = propagate(w, b, X, Y)
print ("dw = " + str(grads["dw"]))
print ("db = " + str(grads["db"]))
print ("cost = " + str(cost))

6 python实现梯度下降

import random
import matplotlib.pyplot as plt

#x轴对应的点
_x = [i/100 for i in range(100)]
#y轴对应的点
_y =  [3*e+4+random.random() for e in _x]


# c for b in a
# 首先for b in a 很好理解：我们从a里面取出每一个迭代对象b。
# 然后我们对这个b进行c操作，并且以c操作后的形式输出一个列表。


plt.show()

w = random.random()
b = random.random()

plt.ion()

for i in range(30):
    for x,y in zip(_x,_y):
        z = x*w+b
        o = z-y
        loss = o**2

        dw = -2*o*x

        db = -2*o

        w = w + 0.1*dw
        b = b+0.1*db
        print(w,b,loss)
        # 清除其他的活動軸
        plt.cla()
        plt.plot(_x,_y,".")

        v = [w*e+b for e in _x]

        plt.plot(_x,v)

        plt.pause(0.01)
plt.ioff()

plt.show()