Andrew Ng Deep Learning 第二课 第二周
前言
网易云课堂(双语字幕,不卡):https://mooc.study.163.com/smartSpec/detail/1001319001.htmcourseId=1004570029、
Coursera(贵):https://www.coursera.org/specializations/deep-learning
本人初学者,先在网易云课堂上看网课,再去Coursera上做作业,开博客以记录,文章中引用图片皆为课程中所截。
题目转载至:http://www.cnblogs.com/hezhiyao/p/7810725.html
编程作业所需库:链接:https://pan.baidu.com/s/1aS1Oia2fskemBHHEMnSepw 密码:66gd
优化算法
Mini-batch 梯度下降
Tips:简单来说就是把一个大训练集分割成多个小训练集后进行梯度下降
Adam优化算法
Momentum梯度下降
指数加权平均
Tips:对每个数据进行线性关联加工,β是超参数
Momentum算法
RMSprop
Adam算法
Tips:ε是为了防止分母有0的情况
学习率递减
Tips:Decay-rate是一个超参数,后面是迭代次数
编程作业
import numpy as np
import matplotlib.pyplot as plt
import scipy.io
import math
import sklearn
import sklearn.datasets
import testCase
from opt_utils import load_params_and_grads, initialize_parameters, forward_propagation, backward_propagation
from opt_utils import compute_cost, predict, predict_dec, plot_decision_boundary, load_dataset
%matplotlib inline
plt.rcParams['figure.figsize'] = (7.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
def update_parameters_with_gd(parameters,grads,learning_rate):
"""
使用梯度下降更新参数
参数:
parameters - 字典,包含了要更新的参数:
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
grads - 字典,包含了每一个梯度值用以更新参数
grads['dW' + str(l)] = dWl
grads['db' + str(l)] = dbl
learning_rate - 学习率
返回值:
parameters - 字典,包含了更新后的参数
"""
L = len(parameters) // 2
# Update rule for each parameter
for l in range(L):
### START CODE HERE ### (approx. 2 lines)
parameters["W" + str(l +1)] = parameters["W" + str(l + 1)] - learning_rate * grads["dW" + str(l + 1)]
parameters["b" + str(l +1)] = parameters["b" + str(l + 1)] - learning_rate * grads["db" + str(l + 1)]
### END CODE HERE ###
return parameters
def random_mini_batches(X,Y,mini_batch_size=64,seed=0):
"""
从(X,Y)中创建一个随机的mini-batch列表
参数:
X - 输入数据,维度为(输入节点数量,样本的数量)
Y - 对应的是X的标签,【1 | 0】(蓝|红),维度为(1,样本的数量)
mini_batch_size - 每个mini-batch的样本数量
返回:
mini-bacthes - 一个同步列表,维度为(mini_batch_X,mini_batch_Y)
"""
np.random.seed(seed) # To make your "random" minibatches the same as ours
m = X.shape[1] # number of training examples m=148
mini_batches = []
# Step 1: Shuffle (X, Y)
permutation = list(np.random.permutation(m))
shuffled_X = X[:, permutation]
shuffled_Y = Y[:, permutation].reshape((1,m))
# Step 2: Partition (shuffled_X, shuffled_Y). Minus the end case.
num_complete_minibatches = math.floor(m/mini_batch_size) # number of mini batches of size mini_batch_size in your partitionning =2
for k in range(0, num_complete_minibatches):
### START CODE HERE ### (approx. 2 lines)
mini_batch_X = shuffled_X[:,k * mini_batch_size:(k+1)*mini_batch_size]
mini_batch_Y = shuffled_Y[:,k * mini_batch_size:(k+1)*mini_batch_size]
### END CODE HERE ###
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
# Handling the end case (last mini-batch < mini_batch_size)
if m % mini_batch_size != 0:
### START CODE HERE ### (approx. 2 lines)
mini_batch_X = shuffled_X[:,num_complete_minibatches * mini_batch_size:] # 64*2:148
mini_batch_Y = shuffled_Y[:,num_complete_minibatches * mini_batch_size:] #62*2:148
### END CODE HERE ###
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
return mini_batches
def initialize_velocity(parameters):
"""
初始化速度,velocity是一个字典:
- keys: "dW1", "db1", ..., "dWL", "dbL"
- values:与相应的梯度/参数维度相同的值为零的矩阵。
参数:
parameters - 一个字典,包含了以下参数:
parameters["W" + str(l)] = Wl
parameters["b" + str(l)] = bl
返回:
v - 一个字典变量,包含了以下参数:
v["dW" + str(l)] = dWl的速度
v["db" + str(l)] = dbl的速度
"""
L = len(parameters) // 2
v = {}
# Initialize velocity
for l in range(L):
### START CODE HERE ### (approx. 2 lines)
v["dW" + str(l+1)] = np.zeros(( parameters['W' + str(l+1)].shape))
v["db" + str(l+1)] = np.zeros(( parameters['b' + str(l+1)].shape))
### END CODE HERE ###
return v
def update_parameters_with_momentun(parameters,grads,v,beta,learning_rate):
"""
使用动量更新参数
参数:
parameters - 一个字典类型的变量,包含了以下字段:
parameters["W" + str(l)] = Wl
parameters["b" + str(l)] = bl
grads - 一个包含梯度值的字典变量,具有以下字段:
grads["dW" + str(l)] = dWl
grads["db" + str(l)] = dbl
v - 包含当前速度的字典变量,具有以下字段:
v["dW" + str(l)] = ...
v["db" + str(l)] = ...
beta - 超参数,动量,实数
learning_rate - 学习率,实数
返回:
parameters - 更新后的参数字典
v - 包含了更新后的速度变量
"""
L = len(parameters) // 2 # number of layers in the neural networks
# Momentum update for each parameter
for l in range(L):
### START CODE HERE ### (approx. 4 lines)
# compute velocities
v["dW" + str(l+1)] = beta*v["dW"+str(l+1)]+(1-beta)*grads["dW"+str(l+1)]
v["db" + str(l+1)] = beta*v["db"+str(l+1)]+(1-beta)*grads["db"+str(l+1)]
# update parameters
parameters["W" + str(l+1)] -= learning_rate*v["dW" + str(l+1)]
parameters["b" + str(l+1)] -= learning_rate*v["db" + str(l+1)]
### END CODE HERE ###
return parameters, v
def initialize_adam(parameters):
"""
初始化v和s,它们都是字典类型的变量,都包含了以下字段:
- keys: "dW1", "db1", ..., "dWL", "dbL"
- values:与对应的梯度/参数相同维度的值为零的numpy矩阵
参数:
parameters - 包含了以下参数的字典变量:
parameters["W" + str(l)] = Wl
parameters["b" + str(l)] = bl
返回:
v - 包含梯度的指数加权平均值,字段如下:
v["dW" + str(l)] = ...
v["db" + str(l)] = ...
s - 包含平方梯度的指数加权平均值,字段如下:
s["dW" + str(l)] = ...
s["db" + str(l)] = ...
"""
L = len(parameters) // 2 # number of layers in the neural networks
v = {}
s = {}
# Initialize v, s. Input: "parameters". Outputs: "v, s".
for l in range(L):
### START CODE HERE ### (approx. 4 lines)
v["dW" + str(l+1)] = np.zeros(( parameters["W" + str(l+1)].shape))
v["db" + str(l+1)] = np.zeros(( parameters["b" + str(l+1)].shape))
s["dW" + str(l+1)] = np.zeros(( parameters["W" + str(l+1)].shape))
s["db" + str(l+1)] = np.zeros(( parameters["b" + str(l+1)].shape))
### END CODE HERE ###
return v, s
def update_parameters_with_adam(parameters,grads,v,s,t,learning_rate=0.01,beta1=0.9,beta2=0.999,epsilon=1e-8):
"""
使用Adam更新参数
参数:
parameters - 包含了以下字段的字典:
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
grads - 包含了梯度值的字典,有以下key值:
grads['dW' + str(l)] = dWl
grads['db' + str(l)] = dbl
v - Adam的变量,第一个梯度的移动平均值,是一个字典类型的变量
s - Adam的变量,平方梯度的移动平均值,是一个字典类型的变量
t - 当前迭代的次数
learning_rate - 学习率
beta1 - 动量,超参数,用于第一阶段,使得曲线的Y值不从0开始(参见天气数据的那个图)
beta2 - RMSprop的一个参数,超参数
epsilon - 防止除零操作(分母为0)
返回:
parameters - 更新后的参数
v - 第一个梯度的移动平均值,是一个字典类型的变量
s - 平方梯度的移动平均值,是一个字典类型的变量
"""
L = len(parameters) // 2 # number of layers in the neural networks
v_corrected = {} # Initializing first moment estimate, python dictionary
s_corrected = {} # Initializing second moment estimate, python dictionary
# Perform Adam update on all parameters
for l in range(L):
# Moving average of the gradients. Inputs: "v, grads, beta1". Output: "v".
### START CODE HERE ### (approx. 2 lines)
v["dW"+str(l+1)]=beta1*v["dW"+str(l+1)]+(1-beta1)*grads["dW"+str(l+1)]
v["db"+str(l+1)]=beta1*v["db"+str(l+1)]+(1-beta1)*grads["db"+str(l+1)]
### END CODE HERE ###
# Compute bias-corrected first moment estimate. Inputs: "v, beta1, t". Output: "v_corrected".
### START CODE HERE ### (approx. 2 lines)
v_corrected["dW"+str(l+1)]=v["dW"+str(l+1)]/(1-math.pow(beta1,t))
v_corrected["db"+str(l+1)]=v["db"+str(l+1)]/(1-math.pow(beta1,t))
### END CODE HERE ###
# Moving average of the squared gradients. Inputs: "s, grads, beta2". Output: "s".
### START CODE HERE ### (approx. 2 lines)
s["dW"+str(l+1)]=beta2*s["dW"+str(l+1)]+(1-beta2)*(grads["dW"+str(l+1)]**2)
s["db"+str(l+1)]=beta2*s["db"+str(l+1)]+(1-beta2)*(grads["db"+str(l+1)]**2)
### END CODE HERE ###
# Compute bias-corrected second raw moment estimate. Inputs: "s, beta2, t". Output: "s_corrected".
### START CODE HERE ### (approx. 2 lines)
s_corrected["dW"+str(l+1)]=s["dW"+str(l+1)]/(1-math.pow(beta2,t))
s_corrected["db"+str(l+1)]=s["db"+str(l+1)]/(1-math.pow(beta2,t))
### END CODE HERE ###
# Update parameters. Inputs: "parameters, learning_rate, v_corrected, s_corrected, epsilon". Output: "parameters".
### START CODE HERE ### (approx. 2 lines)
parameters["W" + str(l + 1)] = parameters["W" + str(l + 1)] - learning_rate * (v_corrected["dW" + str(l + 1)] / np.sqrt(s_corrected["dW" + str(l + 1)] + epsilon))
parameters["b" + str(l + 1)] = parameters["b" + str(l + 1)] - learning_rate * (v_corrected["db" + str(l + 1)] / np.sqrt(s_corrected["db" + str(l + 1)] + epsilon))
### END CODE HERE ###
return parameters, v, s
def model(X,Y,layers_dims,optimizer,learning_rate=0.0007,
mini_batch_size=64,beta=0.9,beta1=0.9,beta2=0.999,
epsilon=1e-8,num_epochs=10000,print_cost=True,is_plot=True):
"""
可以运行在不同优化器模式下的3层神经网络模型。
参数:
X - 输入数据,维度为(2,输入的数据集里面样本数量)
Y - 与X对应的标签
layers_dims - 包含层数和节点数量的列表
optimizer - 字符串类型的参数,用于选择优化类型,【 "gd" | "momentum" | "adam" 】
learning_rate - 学习率
mini_batch_size - 每个小批量数据集的大小
beta - 用于动量优化的一个超参数
beta1 - 用于计算梯度后的指数衰减的估计的超参数
beta1 - 用于计算平方梯度后的指数衰减的估计的超参数
epsilon - 用于在Adam中避免除零操作的超参数,一般不更改
num_epochs - 整个训练集的遍历次数,(视频2.9学习率衰减,1分55秒处,视频中称作“代”),相当于之前的num_iteration
print_cost - 是否打印误差值,每遍历1000次数据集打印一次,但是每100次记录一个误差值,又称每1000代打印一次
is_plot - 是否绘制出曲线图
返回:
parameters - 包含了学习后的参数
"""
L = len(layers_dims) # number of layers in the neural networks
costs = [] # to keep track of the cost
t = 0 # initializing the counter required for Adam update
seed = 10 # For grading purposes, so that your "random" minibatches are the same as ours
# Initialize parameters
parameters = initialize_parameters(layers_dims)
# Initialize the optimizer
if optimizer == "gd":
pass # no initialization required for gradient descent
elif optimizer == "momentum":
v = initialize_velocity(parameters)
elif optimizer == "adam":
v, s = initialize_adam(parameters)
# Optimization loop
for i in range(num_epochs):
# Define the random minibatches. We increment(增加) the seed to reshuffle(重新洗牌) differently the dataset after each epoch
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# Forward propagation
a3, caches = forward_propagation(minibatch_X, parameters)
# Compute cost
cost = compute_cost(a3, minibatch_Y)
# Backward propagation
grads = backward_propagation(minibatch_X, minibatch_Y, caches)
# Update parameters
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads, learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentum(parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1 # Adam counter
parameters, v, s = update_parameters_with_adam(parameters, grads, v, s,
t, learning_rate, beta1, beta2, epsilon)
# Print the cost every 1000 epoch
if print_cost and i % 1000 == 0:
print ("Cost after epoch %i: %f" %(i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
train_X, train_Y = load_dataset(is_plot=False)
layers_dims = [train_X.shape[0], 5, 2, 1]
#使用Adam优化的梯度下降
parameters = model(train_X, train_Y, layers_dims, optimizer="adam",is_plot=True)
题目