吴恩达神经网络与深度学习——深度神经网络习题4：构建DNN架构

构建DNN架构

a^[l]:第l层的激活函数
w^[l]，b^[l]:第l层的参数
x^(i):第i个训练样本
a^[l]_i：第l层第i个神经元的激活函数

包

numpy
matplotlib
dnn_utils

import numpy as np
import h5py
import matplotlib.pyplot as plt
from testCases_v2 import *
from dnn_utils_v2 import sigmoid, sigmoid_backward, relu, relu_backward

%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

%load_ext autoreload
%autoreload 2

np.random.seed(1)

作业大纲

建一个2层NN和一个L层NN
	1.初始化参数
	2.实现前向传播
		实现一个线性部分(Z^[l])
		实现激活函数(ReLu/sigmoid)
		将前两步结合起来，形成[LINEAR->ACTIVATION]正向传播
		复制L-1次，最后一次使用[LINEAR->sigmoid]正向传播
	3.计算损失函数
	4.实现反向传播
		完成反向传播的线性部分
		计算激活函数的导数(relu_backward/sigmoid_backward) 
		结合前两步，形成 [LINEAR->ACTIVATION] 反向传播
		复制L-1次，最后一次使用[LINEAR->sigmoid]反向传播
	5.更新参数
		

初始化

2层NN

import numpy as np
def initialize_parameters(n_x, n_h, n_y):
    '''
    input:
        n_x:input layer size
        n_h:hidden layer size
        n_y:outpou layer size
    output:
        parameters:which combine W1,W2,b1,b2
        W1,b1:1th layer parameters
           W1.shape = n_h,n_x
           b1.shape = n_h,1
        W2,b2:2th layer parameters
           W2.shape = n_y,n_h
           b2.shape = n_y,1
    '''
    np.random.seed(1)
    W1 = np.random.randn(n_h, n_x) * 0.01
    W2 = np.random.randn(n_y, n_h) * 0.01
    b1 = np.zeros((n_h, 1))
    b2 = np.zeros((n_y, 1))

    assert (W1.shape == (n_h, n_x))
    assert (W2.shape == (n_y, n_h))
    assert (b1.shape == (n_h, 1))
    assert (b2.shape == (n_y, 1))
    parameters = {
        "W1": W1,
        "W2": W2,
        "b1": b1,
        "b2": b2}
    return parameters
parameters = initialize_parameters(2,2,1)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))

L层NN

import two_layer_nn
import  numpy as np
def initialize_parameters_deep(layer_dims):
    '''
    input:
        layer_dims:python array (list) containing the dimensions of each layer in our network
            example:layer_dims = [2,4,1]means it's a 2 layer NN,input layer has 2 units,hidden layer has 4 units,output layer has 1 unit
    output:
        :parameters: which combines W1,b1,W2,b2,...,WL,bL
            W1.shape = n1,n0   b1.shape = n1,1
            W2.shape = n2,n1   b2.shape = n2,1
            ...
            WL.shape = nL,nL-1,bL.shape = nL,1

    '''
    np.random.seed(3)
    parameters = {}
    L = len(layer_dims)
    for i in range(1,L):
        parameters["W"+str(i)] = np.random.randn(layer_dims[i],layer_dims[i-1])*0.01
        parameters["b"+str(i)] = np.zeros((layer_dims[i],1))
        assert (parameters["W"+str(i)].shape == (layer_dims[i],layer_dims[i-1]))
        assert (parameters["b"+str(i)].shape == (layer_dims[i],1))

    return  parameters
parameters = initialize_parameters_deep([5,4,3])
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))

前向传播