2019.10.8学习进度
**今天是第10天参与STAR Pro,今天主要完成了week2大作业——Logistic Regression as a Neural Network的剩余部分:
**
4.3 - Forward and Backward propagation
构造函数propagate(),计算出损失函数及神经网络的梯度
代码:
GRADED FUNCTION: propagate
# GRADED FUNCTION: propagate
import numpy as np
def propagate(w, b, X, Y):
m = X.shape[1]
# FORWARD PROPAGATION (FROM X TO COST)
### START CODE HERE ### (≈ 2 lines of code)
A = sigmoid(np.dot(w.T,X)+b) #注意这里w要转置 # compute activation
cost = (- 1 / m) * np.sum(Y * np.log(A) + (1 - Y) * (np.log(1 - A))) #这里Y与log(A)直接相乘即可 # compute cost
### END CODE HERE ###
# BACKWARD PROPAGATION (TO FIND GRAD)
### START CODE HERE ### (≈ 2 lines of code)
dw = (1/m)*np.dot(X,(A-Y).T) #np.dot使用过程要注意两个矩阵的维度
db = (1/m)*np.sum(A-Y)
### END CODE HERE ###
assert(dw.shape == w.shape)
assert(db.dtype == float)
cost = np.squeeze(cost)
assert(cost.shape == ())
grads = {"dw": dw,
"db": db}
return grads, cost
输出结果
4.4 -Optimization
使用梯度下降法,迭代优化参数w和b。
代码:
# GRADED FUNCTION: optimize
import numpy as np
def optimize(w, b, X, Y, num_iterations, learning_rate, print_cost = False):
costs = []
for i in range(num_iterations):
# Cost and gradient calculation (≈ 1-4 lines of code)
### START CODE HERE ###
grads, cost = propagate(w, b, X, Y)
### END CODE HERE ###
# Retrieve derivatives from grads
dw = grads["dw"]
db = grads["db"]
# update rule (≈ 2 lines of code)
### START CODE HERE ###
w = w-learning_rate*dw
b = b-learning_rate*db
### END CODE HERE ###
# Record the costs
if i % 100 == 0:
costs.append(cost)
# Print the cost every 100 training iterations
if print_cost and i % 100 == 0:
print ("Cost after iteration %i: %f" %(i, cost))
params = {"w": w,
"b": b}
grads = {"dw": dw,
"db": db}
return params, grads, costs #将输出结果储存在dict中
结果:
在上几个函数的基础上,得到Y的预期值函数
代码
# GRADED FUNCTION: predict
import numpy as np
def predict(w, b, X):
'''
m = X.shape[1]
Y_prediction = np.zeros((1,m))
w = w.reshape(X.shape[0], 1)
# Compute vector "A" predicting the probabilities of a cat being present in the picture
### START CODE HERE ### (≈ 1 line of code)
A = sigmoid(np.dot(w.T,X)+b)
### END CODE HERE ###
for i in range(A.shape[1]):
# Convert probabilities A[0,i] to actual predictions p[0,i]
### START CODE HERE ### (≈ 4 lines of code)
if A[0,i]<=0.5 :
Y_prediction[0,i]=0
else :
Y_prediction[0,i]=1
### END CODE HERE ###
assert(Y_prediction.shape == (1, m))
return Y_prediction
5 - Merge all functions into a model
综合本次作业写的函数进一个model中,
代码:
# GRADED FUNCTION: model
import numpy as np
def model(X_train, Y_train, X_test, Y_test, num_iterations = 2000, learning_rate = 0.5, print_cost = False):
### START CODE HERE ###
# initialize parameters with zeros (≈ 1 line of code)
w, b = initialize_with_zeros(X_train.shape[0])
# Gradient descent (≈ 1 line of code)
parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost = False)
# Retrieve parameters w and b from dictionary "parameters"
w = parameters["w"] #获取参数
b = parameters["b"]
# Predict test/train set examples (≈ 2 lines of code)
Y_prediction_test = predict(w, b, X_test) #计算出预测值
Y_prediction_train = predict(w, b, X_train)
### END CODE HERE ###
# Print train/test Errors
print("train accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_train - Y_train)) * 100))
print("test accuracy: {} %".format(100 - np.mean(np.abs(Y_prediction_test - Y_test)) * 100))
d = {"costs": costs,
"Y_prediction_test": Y_prediction_test,
"Y_prediction_train" : Y_prediction_train,
"w" : w,
"b" : b,
"learning_rate" : learning_rate,
"num_iterations": num_iterations}
return d
输出结果:
碰到问题:
1.不明白权重参数W和偏置参数b的维度是如何决定的
2.不明白numpy中矩阵的维度等参数是如何排序的?
2019.10.9学习进度
今天是第天11参加STAR Pro,今天主要完成了编程作业week3——Planar_data_classification_with_onehidden_layer_v6c ,了解了2layer NN是如何通过编程实现的
4 - Neural Network model
4.1 - Defining the neural network structure
本小节构造了一个返回神经网络输入输出维度的函数
代码如下:
# GRADED FUNCTION: layer_sizes
def layer_sizes(X, Y):
### START CODE HERE ### (≈ 3 lines of code)
n_x = X.shape[0]# size of input layer
n_h = 4
n_y = Y.shape[0] # size of output layer
### END CODE HERE ###
return (n_x, n_h, n_y)
结果:
4.2 - Initialize the model’s parameters
本小节构造了一个初始化权重参数w与偏置参数b,其维度与所在层的n值有关
代码如下:
# GRADED FUNCTION: initialize_parameters
import numpy as np
def initialize_parameters(n_x, n_h, n_y): #初始化参数W1、b1、W2、b2
np.random.seed(2) # we set up a seed so that your output matches ours although the initialization is random.
### START CODE HERE ### (≈ 4 lines of code)
W1 = np.random.randn(n_h,n_x) * 0.01 #初始化w后要乘以一个小数
b1 = np.zeros((n_h,1))
W2 = np.random.randn(n_y,n_h) * 0.01 #注意W2的维度为(n_y,n_h)
b2 = np.zeros((n_y,1))
### END CODE HERE ###
assert (W1.shape == (n_h, n_x))
assert (b1.shape == (n_h, 1))
assert (W2.shape == (n_y, n_h))
assert (b2.shape == (n_y, 1))
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
结果如下:
4.3 - The Loop
本小节通过神经网络的正向传播计算出预值、参数导数,再由梯度下降,推出反向传播,优化各个参数。
forward_propagation
代码:
# GRADED FUNCTION: forward_propagation
import numpy as np
def forward_propagation(X, parameters): #双层神经网络正向传播,返回值为Z1、A1、Z2、A2
# Retrieve each parameter from the dictionary "parameters"
### START CODE HERE ### (≈ 4 lines of code)
W1 = parameters["W1"] #python中dict用法,直接输入元素名即可获取元素值
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
### END CODE HERE ###
# Implement Forward Propagation to calculate A2 (probabilities)
### START CODE HERE ### (≈ 4 lines of code)
Z1 = np.dot(W1,X)+b1 #为什么这里不用转置W1??
A1 = np.tanh(Z1) #第一层的输出作为第二层的输入
Z2 = np.dot(W2,A1)+b2 #为了达到expected output,在尝试多次以后第一次激活函数使用tanh() ,第二次使用sigmoid()
A2 = sigmoid(Z2)
### END CODE HERE ###
assert(A2.shape == (1, X.shape[1]))
cache = {"Z1": Z1,
"A1": A1,
"Z2": Z2,
"A2": A2}
return A2, cache
结果如下:
compute_cost
代码如下:
# GRADED FUNCTION: compute_cost
import numpy as np
def compute_cost(A2, Y, parameters): #cost函数的计算
m = Y.shape[1] # number of example
# Compute the cross-entropy cost
### START CODE HERE ### (≈ 2 lines of code)
logprobs = np.multiply(np.log(A2),Y)+np.multiply(np.log(1-A2),1-Y) #使用np.multipy函数,不用对矩阵进行转置,实现了对应元素相乘
cost = -(1/m)*np.sum(logprobs)
### END CODE HERE ###
cost = float(np.squeeze(cost)) # makes sure cost is the dimension we expect.
# E.g., turns [[17]] into 17
assert(isinstance(cost, float))
return cost
结果如下:
backward_propagation
代码如下:
# GRADED FUNCTION: backward_propagation
import numpy as np
def backward_propagation(parameters, cache, X, Y): #反向传播过程
m = X.shape[1]
# First, retrieve W1 and W2 from the dictionary "parameters".
### START CODE HERE ### (≈ 2 lines of code)
W1 = parameters["W1"]
W2 = parameters["W2"]
### END CODE HERE ###
# Retrieve also A1 and A2 from dictionary "cache".
### START CODE HERE ### (≈ 2 lines of code)
A1 = cache["A1"]
A2 = cache["A2"]
### END CODE HERE ###
# Backward propagation: calculate dW1, db1, dW2, db2.
### START CODE HERE ### (≈ 6 lines of code, corresponding to 6 equations on slide above)
dZ2 = A2-Y #依照公式,计算出各个微元,为后续参数优化(梯度下降法)做准备
dW2 = (1/m)*np.dot(dZ2,A1.T)
db2 = (1/m)*np.sum(dZ2,axis=1,keepdims=True)
dZ1 = np.dot(W2.T,dZ2)*(1 - np.power(A1, 2))
dW1 = (1/m)*np.dot(dZ1,X.T)
db1 = (1/m)*np.sum(dZ1,axis=1,keepdims=True)
### END CODE HERE ###
grads = {"dW1": dW1,
"db1": db1,
"dW2": dW2,
"db2": db2}
return grads
结果如下:
update_parameters(优化参数)
代码如下:
# GRADED FUNCTION: update_parameters
def update_parameters(parameters, grads, learning_rate = 1.2):
# Retrieve each parameter from the dictionary "parameters"
### START CODE HERE ### (≈ 4 lines of code)
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
### END CODE HERE ###
# Retrieve each gradient from the dictionary "grads"
### START CODE HERE ### (≈ 4 lines of code)
dW1 = grads["dW1"]
db1 = grads["db1"]
dW2 = grads["dW2"]
db2 = grads["db2"]
## END CODE HERE ###
# Update rule for each parameter
### START CODE HERE ### (≈ 4 lines of code)
W1 = W1-learning_rate*dW1 #此处学习率为默认参数
b1 = b1-learning_rate*db1
W2 = W2-learning_rate*dW2
b2 = b2-learning_rate*db2
### END CODE HERE ###
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
结果如下:
4.4 - Integrate parts 4.1, 4.2 and 4.3 in nn_model()
代码如下:
# GRADED FUNCTION: nn_model
import numpy as np
def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False): #封装之前定义的函数
np.random.seed(3)
n_x = layer_sizes(X, Y)[0]
n_y = layer_sizes(X, Y)[2]
# Initialize parameters
### START CODE HERE ### (≈ 1 line of code)
parameters = initialize_parameters(n_x, n_h, n_y)
### END CODE HERE ###
# Loop (gradient descent)
for i in range(0, num_iterations):
### START CODE HERE ### (≈ 4 lines of code)
# Forward propagation. Inputs: "X, parameters". Outputs: "A2, cache".
A2, cache = #返回正向传播得到的参数
# Cost function. Inputs: "A2, Y, parameters". Outputs: "cost".
cost = compute_cost(A2, Y, parameters) #计算出cost函数
# Backpropagation. Inputs: "parameters, cache, X, Y". Outputs: "grads".
grads = backward_propagation(parameters, cache, X, Y) #反向传播计算出梯度
# Gradient descent parameter update. Inputs: "parameters, grads". Outputs: "parameters".
parameters = update_parameters(parameters, grads) #梯度下降法迭代,优化参数
### END CODE HERE ###
# Print the cost every 1000 iterations
if print_cost and i % 1000 == 0:
print ("Cost after iteration %i: %f" %(i, cost))
return parameters
结果如下:
4.5 Predictions
代码如下:
# GRADED FUNCTION: predict
import numpy as np
def predict(parameters, X):
# Computes probabilities using forward propagation, and classifies to 0/1 using 0.5 as the threshold.
### START CODE HERE ### (≈ 2 lines of code)
A2, cache = forward_propagation(X, parameters)
predictions = np.around(A2) #此处用around函数可以返回四舍五入后的值
### END CODE HERE ###
return predictions
结果如下:
参考:
https://blog.youkuaiyun.com/tz_zs/article/details/80775256
https://blog.youkuaiyun.com/tz_zs/article/details/90209220
碰到问题:
1.神经网络中权重参数w和偏置参数b的维度应该如何确定?(有时在dot函数中需要转置,有时却不需要。)
2.
2019.10.10学习进度
今天是第12天参加STAR Pro,今天主要完成了两件事。
深层神经网络的学习
了解了深层神经网络的概念,与浅层神经网比较,深层神经网的优势、深层网络中的前向传播,以及学习了矩阵的维数应该怎么设立,解决了我前两天碰到的问题。
week4大作业——Building_your_Deep_Neural_Network_Step_by_Step_v8a
今天完成了本次大作业Part1的1~5,基于上几次作业的基础,由logistic回归、浅层神经网络,到本次的深层神经网络,由浅到深。
3 - Initialization
3.1 - 2-layer Neural Network
本小节回顾了一下双层神经网络的参数维度的设置
代码:
# GRADED FUNCTION: initialize_parameters
import numpy as np
import random
from random import randint
def initialize_parameters(n_x, n_h, n_y):
np.random.seed(1) #seed( ) 用于指定随机数生成时所用算法开始的整数值,如果使用相同的seed( )值,则每次生成的随即数都相同
### START CODE HERE ### (≈ 4 lines of code)
W1 = np.random.randn(n_h,n_x)*0.01
b1 = np.zeros((n_h, 1)) #注意np.zeros()函数里面参数也要加括号
W2 = np.random.randn(n_y,n_h)*0.01
b2 = np.zeros((n_y, 1))
### END CODE HERE ###
assert(W1.shape == (n_h, n_x))
assert(b1.shape == (n_h, 1))
assert(W2.shape == (n_y, n_h))
assert(b2.shape == (n_y, 1))
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
结果:
3.2 - L-layer Neural Network
由双层神经网络引申到L层的深层神经网络
代码:
**初始化参数**
# GRADED FUNCTION: initialize_parameters_deep
import numpy as np
def initialize_parameters_deep(layer_dims):
np.random.seed(3)
parameters = {}
L = len(layer_dims) # number of layers in the network
for l in range(1, L):
### START CODE HERE ### (≈ 2 lines of code)
parameters['W' + str(l)] = np.random.randn(layer_dims[l],layer_dims[l-1]) * 0.01 #layer_dims存储了不同层的n值
parameters['b' + str(l)] = np.zeros((layer_dims[l],1))
### END CODE HERE ###
assert(parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l-1]))
assert(parameters['b' + str(l)].shape == (layer_dims[l], 1))
return parameters
结果:
4 - Forward propagation module
4.1 - Linear Forward
代码:
# GRADED FUNCTION: linear_forward
import numpy as np
def linear_forward(A, W, b):
"""
Implement the linear part of a layer's forward propagation.
Arguments:
A -- activations from previous layer (or input data): (size of previous layer, number of examples)
W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
b -- bias vector, numpy array of shape (size of the current layer, 1)
Returns:
Z -- the input of the activation function, also called pre-activation parameter
cache -- a python tuple containing "A", "W" and "b" ; stored for computing the backward pass efficiently
"""
### START CODE HERE ### (≈ 1 line of code)
Z = np.dot(W,A)+b
### END CODE HERE ###
assert(Z.shape == (W.shape[0], A.shape[1]))
cache = (A, W, b)
return Z, cache
结果:
4.2 - Linear-Activation Forward
本小节设立了两种激活函数的调用以及输出的函数。
代码:
# GRADED FUNCTION: linear_activation_forward
def linear_activation_forward(A_prev, W, b, activation):
if activation == "sigmoid":
# Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
### START CODE HERE ### (≈ 2 lines of code)
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = sigmoid(Z) # a"cache" contains "Z" (it's what we will feed in to the corresponding backward function).
### END CODE HERE ###
elif activation == "relu":
# Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
### START CODE HERE ### (≈ 2 lines of code)
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = relu(Z)
### END CODE HERE ###
assert (A.shape == (W.shape[0], A_prev.shape[1]))
cache = (linear_cache, activation_cache)
return A, cache
结果:
d) L-Layer Model
代码:
# GRADED FUNCTION: L_model_forward
def L_model_forward(X, parameters):
caches = []
A = X
L = len(parameters) // 2 # number of layers in the neural network
# Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
for l in range(1, L):
A_prev = A
### START CODE HERE ### (≈ 2 lines of code)
A, cache = linear_activation_forward(A_prev, parameters["W"+str(l)], parameters["b"+str(l)], activation = "relu")
caches.append(cache)
### END CODE HERE ###
# Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
### START CODE HERE ### (≈ 2 lines of code)
AL, cache = linear_activation_forward(A, parameters["W"+str(L)], parameters["b"+str(L)], activation = "sigmoid") #此时A为A[L-1]
caches.append(cache)
### END CODE HERE ###
assert(AL.shape == (1,X.shape[1]))
return AL, caches
结果:
5 - Cost function
计算出损失函数
代码:
# GRADED FUNCTION: compute_cost
import numpy as np
def compute_cost(AL, Y):
"""
Implement the cost function defined by equation (7).
Arguments:
AL -- probability vector corresponding to your label predictions, shape (1, number of examples)
Y -- true "label" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples)
Returns:
cost -- cross-entropy cost
"""
m = Y.shape[1]
# Compute loss from aL and y.
### START CODE HERE ### (≈ 1 lines of code)
cost =(-1/m)*np.sum(Y*np.log(AL)+(1-Y)*np.log(1-AL))
### END CODE HERE ###
cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17).
assert(cost.shape == ())
return cost
结果:
2019.10.11学习进度
今天是第十三天参与STAR Pro,今天主要完成了两方面内容
深层神经网络
学习完了深层神经网络的剩余内容,了解了深层神经网络的模块是如何搭建的,还有一些参数的概念,最后了解了神经网络与大脑的关系
week4编程作业
今天完成了week4编程作业的所有内容,学习了深层神经网络各个模块的搭建,最后集于一个model中。
Building your Deep Neural Network: Step by Step
继昨天的进度,今天完成了剩余内容。
6 - Backward propagation module
6.1 - Linear backward
代码:
GRADED FUNCTION: linear_backward
import numpy as np
def linear_backward(dZ, cache):
A_prev, W, b = cache
m = A_prev.shape[1]
### START CODE HERE ### (≈ 3 lines of code)
dW = (1/m)*np.dot(dZ,A_prev.T) #注意计算dW和dA时候需要转置矩阵
db = (1/m)*np.sum(dZ,axis=1,keepdims=True)
dA_prev =np.dot(W.T,dZ)
### END CODE HERE ###
assert (dA_prev.shape == A_prev.shape)
assert (dW.shape == W.shape)
assert (db.shape == b.shape)
return dA_prev, dW, db
结果:
6.2 - Linear-Activation backward
代码:
# GRADED FUNCTION: linear_activation_backward
def linear_activation_backward(dA, cache, activation):
linear_cache, activation_cache = cache #这里cache储存了两种cache,一个为参数另一个为超参数
if activation == "relu":
### START CODE HERE ### (≈ 2 lines of code)
dZ = relu_backward(dA, activation_cache) #这个两个函数是自带的??还是系统为我们定义的?
dA_prev, dW, db = linear_backward(dZ, linear_cache)
### END CODE HERE ###
elif activation == "sigmoid":
### START CODE HERE ### (≈ 2 lines of code)
dZ = dZ = sigmoid_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
### END CODE HERE ###
return dA_prev, dW, db
结果:
6.3 - L-Model Backward
代码:
# GRADED FUNCTION: L_model_backward
import numpy as np
def L_model_backward(AL, Y, caches):
grads = {}
L = len(caches) # the number of layers
m = AL.shape[1]
Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL
# Initializing the backpropagation
### START CODE HERE ### (1 line of code)
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
### END CODE HERE ###
# Lth layer (SIGMOID -> LINEAR) gradients. Inputs: "dAL, current_cache". Outputs: "grads["dAL-1"], grads["dWL"], grads["dbL"]
### START CODE HERE ### (approx. 2 lines)
current_cache =caches[L-1]
grads["dA" + str(L-1)], grads["dW" + str(L)], grads["db" + str(L)] = linear_activation_backward(dAL, current_cache, activation="sigmoid")
### END CODE HERE ###
# Loop from l=L-2 to l=0
for l in reversed(range(L-1)):
# lth layer: (RELU -> LINEAR) gradients.
# Inputs: "grads["dA" + str(l + 1)], current_cache". Outputs: "grads["dA" + str(l)] , grads["dW" + str(l + 1)] , grads["db" + str(l + 1)]
### START CODE HERE ### (approx. 5 lines)
current_cache = caches[l]
dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA"+str(l+1)], current_cache, activation="relu") #注意这里l是从L-1开始递减的
grads["dA" + str(l)] = dA_prev_temp ##这里的current_cacahe储存参数w,b和a_prev
grads["dW" + str(l + 1)] = dW_temp
grads["db" + str(l + 1)] = db_temp
### END CODE HERE ###
return grads
6.4 - Update Parameters
代码:
# GRADED FUNCTION: update_parameters
def update_parameters(parameters, grads, learning_rate):
L = len(parameters) // 2 # number of layers in the neural network
# Update rule for each parameter. Use a for loop.
### START CODE HERE ### (≈ 3 lines of code)
for l in range(L):
parameters["W" + str(l+1)] = parameters["W" + str(l+1)]-learning_rate*grads["dW"+str(l+1)] #grads为L_model_backward(AL, Y, caches)
parameters["b" + str(l+1)] = parameters["b" + str(l+1)]-learning_rate*grads["db"+str(l+1)] #的返回值
### END CODE HERE ###
return parameters
结果:
week4 part1碰到问题:
1.不明白6.3中所存储的是什么?
2.6.2中relu_backward()等激活函数是什么时候定义的?
Deep Neural Network for Image Classification: Application
本节作业综合了上一节作业所定义的函数,应用于一个模块中。学会了深层神经网络在监督学习中的构建与应用。
4 - Two-layer neural network
代码:
# GRADED FUNCTION: two_layer_model
def two_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):
np.random.seed(1)
grads = {}
costs = [] # to keep track of the cost
m = X.shape[1] # number of examples
(n_x, n_h, n_y) = layers_dims
# Initialize parameters dictionary, by calling one of the functions you'd previously implemented
### START CODE HERE ### (≈ 1 line of code)
parameters = initialize_parameters(n_x,n_h,n_y)
### END CODE HERE ###
# Get W1, b1, W2 and b2 from the dictionary parameters.
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Loop (gradient descent)
for i in range(0, num_iterations):
# Forward propagation: LINEAR -> RELU -> LINEAR -> SIGMOID. Inputs: "X, W1, b1, W2, b2". Output: "A1, cache1, A2, cache2".
### START CODE HERE ### (≈ 2 lines of code)
A1, cache1 = linear_activation_forward(X, W1, b1, activation="relu")
A2, cache2 = linear_activation_forward(A1, W2, b2, activation="sigmoid")
### END CODE HERE ###
# Compute cost
### START CODE HERE ### (≈ 1 line of code)
cost = compute_cost(A2,Y)
### END CODE HERE ###
# Initializing backward propagation
dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))
# Backward propagation. Inputs: "dA2, cache2, cache1". Outputs: "dA1, dW2, db2; also dA0 (not used), dW1, db1".
### START CODE HERE ### (≈ 2 lines of code)
dA1, dW2, db2 = linear_activation_backward(dA2,cache2,activation="sigmoid")
dA0, dW1, db1 = linear_activation_backward(dA1,cache1,activation="relu")
### END CODE HERE ###
# Set grads['dWl'] to dW1, grads['db1'] to db1, grads['dW2'] to dW2, grads['db2'] to db2
grads['dW1'] = dW1
grads['db1'] = db1
grads['dW2'] = dW2
grads['db2'] = db2
# Update parameters.
### START CODE HERE ### (approx. 1 line of code)
parameters = update_parameters(parameters, grads,learning_rate)
### END CODE HERE ###
# Retrieve W1, b1, W2, b2 from parameters
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Print the cost every 100 training example
if print_cost and i % 100 == 0:
print("Cost after iteration {}: {}".format(i, np.squeeze(cost)))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per hundreds)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
return parameters
结果:
5 - L-layer Neural Network
代码:
# GRADED FUNCTION: L_layer_model
def L_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):#lr was 0.009
np.random.seed(1)
costs = [] # keep track of cost
# Parameters initialization. (≈ 1 line of code)
### START CODE HERE ###
parameters = initialize_parameters_deep(layers_dims)
### END CODE HERE ###
# Loop (gradient descent)
for i in range(0, num_iterations):
# Forward propagation: [LINEAR -> RELU]*(L-1) -> LINEAR -> SIGMOID.
### START CODE HERE ### (≈ 1 line of code)
AL, caches = L_model_forward(X, parameters)
### END CODE HERE ###
# Compute cost.
### START CODE HERE ### (≈ 1 line of code)
cost = compute_cost(AL, Y)
### END CODE HERE ###
# Backward propagation.
### START CODE HERE ### (≈ 1 line of code)
grads = L_model_backward(AL, Y, caches)
### END CODE HERE ###
# Update parameters.
### START CODE HERE ### (≈ 1 line of code)
parameters = update_parameters(parameters, grads, learning_rate)
### END CODE HERE ###
# Print the cost every 100 training example
if print_cost and i % 100 == 0:
print ("Cost after iteration %i: %f" %(i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per hundreds)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
return parameters
结果:
2019.10.12学习进度
今天是第14天参与STAR Pro,到目前为止,我已经完成了python的基础学习、四周神经网络和深度学习的课程以及相对应四周的编程作业,还有学习了两节机器学习-李宏毅(2019) Machine Learning的内容。
今天开始学习"改善深层神经网络:超参数调试、正则化以及优化"的内容
第一周 深度学习的实用层面
今天学习了前5节知识,主要了解了在搭建深层神经网络时需要做出的决策,以及怎样优化这些参数以提高神经网络的效率。还了解了正则化的概念。
2019.10.13学习进度
今天是第十五天参与STAR Pro,今天主要继昨天的进度,继续学习了深层学习的实用层面的知识。今天主要学了什么是随即失活正则化、其它正则化以及归一化输入,了解了他们的作用原理以及优缺点。