deep_learning_month2_week2_Optimization_methods
标签: 机器学习深度学习
代码已上传github:
https://github.com/PerfectDemoT/my_deeplearning_homework
- deep_learning_month2_week2_Optimization_methods
-
- 这次的题目是优化算法,即使用 monmentum方法以及RMSprop方法,然后最终使用Adam方法(其实Adam算法更像是结合了前面两种算法)
- 1. 我们先导入包
- 2.就像之前说的,我们最后是对三种方法的训练效果进行比较。我们实现普通的参数更新操作
- 3. 接下来我们实现mini-batch算法,另外,在实现这个算法时,我们需要了解一下这些:(批量梯度下降和随机梯度下降不严格的说,其实就是mini-batch的特殊情况)
- 4. 这里我改变一下原来的代码顺序(注意,这一段应该放在最后,只能在预测函数前面)
- 5. 现在我们开始写monmentum(动态梯度下降)算法
- 6. 接下来看Adam优化方法(则种方法像结合monmentum方法以及RMSprop方法,所以这里没有单独谈RMSprop方法)
- 7. 总结一下:
-
这次的题目是优化算法,即使用 monmentum方法以及RMSprop方法,然后最终使用Adam方法(其实Adam算法更像是结合了前面两种算法)
其中很重要的一点是对于 vdw v d w 以及 sdw s d w 的初始化以及迭代运算,另外还有 β1 β 1 与 β2 β 2 的选取(虽然我们会谈到这两个值一般可以不进行筛选,因为其实有两个”通用”的值,一般都直接用这两个值)
最后,我们还将:普通mini-batch下降 , 用momentum的mini-batch梯度下降 , 用Adma的mini-batch梯度下降。三个进行了比较(当然,这里主要是比较其对最后的预测准确度的影响,虽然平常这三种方法往往是看对训练速度的影响)
下面我们来看看实现过程:
1. 我们先导入包
import numpy as np
import matplotlib.pyplot as plt
import scipy.io
import math
import sklearn
import sklearn.datasets
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
from testCases import *
在这里我还是建议在自己实现时,去看看有些写好的功能函数,并且里面其实有需要改动的地方(有几个地方直接用会报错的,是矩阵的大小不对等问题,如果你自己实现的话,一定会遇到,此不赘述)
2.就像之前说的,我们最后是对三种方法的训练效果进行比较。我们实现普通的参数更新操作
#首先是更新参数的函数
# GRADED FUNCTION: update_parameters_with_gd
def update_parameters_with_gd(parameters, grads, learning_rate):
"""
Update parameters using one step of gradient descent
Arguments:
parameters -- python dictionary containing your parameters to be updated:
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
grads -- python dictionary containing your gradients to update each parameters:
grads['dW' + str(l)] = dWl
grads['db' + str(l)] = dbl
learning_rate -- the learning rate, scalar.
Returns:
parameters -- python dictionary containing your updated parameters
"""
L = len(parameters) // 2 # number of layers in the neural networks
# 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
输出测试一下:
#下面来输出看看
parameters, grads, learning_rate = update_parameters_with_gd_test_case()
parameters = update_parameters_with_gd(parameters, grads, learning_rate)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
print("=====================================")
结果是这样:
W1 = [[ 1.63535156 -0.62320365 -0.53718766]
[-1.07799357 0.85639907 -2.29470142]]
b1 = [[ 1.74604067]
[-0.75184921]]
W2 = [[ 0.32171798 -0.25467393 1.46902454]
[-2.05617317 -0.31554548 -0.3756023 ]
[ 1.1404819 -1.09976462 -0.1612551 ]]
b2 = [[-0.88020257]
[ 0.02561572]
[ 0.57539477]]
3. 接下来我们实现mini-batch算法,另外,在实现这个算法时,我们需要了解一下这些:(批量梯度下降和随机梯度下降不严格的说,其实就是mini-batch的特殊情况)
#批量梯度下降和随机梯度下降(其实也就是B=1的mini-batch下法)的伪代码在.ipynb文件里
# - ** (Batch)
#
# ``` python
# X = data_input
# Y = labels
# parameters = initialize_parameters(layers_dims)
# for i in range(0, num_iterations):
# # Forward propagation
# a, caches = forward_propagation(X, parameters)
# # Compute cost.
# cost = compute_cost(a, Y)
# # Backward propagation.
# grads = backward_propagation(a, caches, parameters)
# # Update parameters.
# parameters = update_parameters(parameters, grads)
#
# ```
#
# - ** Stochastic
#
# ```python
# X = data_input
# Y = labels
# parameters = initialize_parameters(layers_dims)
# for i in range(0, num_iterations):
# for j in range(0, m):
# # Forward propagation
# a, caches = forward_propagation(X[:, j], parameters)
# # Compute cost
# cost = compute_cost(a, Y[:, j])
# # Backward propagation
# grads = backward_propagation(a, caches, parameters)
# # Update parameters.
# parameters = update_parameters(parameters, grads)
# ```
接下来我们来看看Mini-batch的代码
#下面我们来实现mini-batch
# GRADED FUNCTION: random_mini_batches
def random_mini_batches(X, Y, mini_batch_size=64, seed=0):
"""
Creates a list of random minibatches from (X, Y)
Arguments:
X -- input data, of shape (input size, number of examples)
Y -- true "label" vector (1 for blue dot / 0 for red dot), of shape (1, number of examples)
mini_batch_size -- size of the mini-batches, integer
Returns:
mini_batches -- list of synchronous (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
mini_batches = []
# Step 1: Shuffle (X, Y) 打乱顺序
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
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) : ]
mini_batch_Y = shuffled_Y[: , (num_complete_minibatches * mini_batch_size) : ]
### END CODE HERE ###
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
return mini_batches
下面我们来简单说明一下上方算法:
上面的思路是,先把X , Y 数据集打乱,然后根据每一个 batch b a t c h 的大小,将m个数据分为 mmini_batch_size m m i n i _ b a t c h _ s i z e 个大小为 mini_catch_size m i n i _ c a t c h _ s i z e 的块,分的方法是用矩阵的划分。然后用 mini_batch m i n i _ b a t c h 将 mini_batch_X m i n i _ b a t c h _ X 与 mini_batch_Y m i n i _ b a t c h _ Y 装在一起,再用语句mini_batches.append(mini_batch)把所有变量装在一个 mini_batches m i n i _ b a t c h e s 里
现在可以测试一下:
#下面来输出看看效果
X_assess, Y_assess, mini_batch_size = random_mini_batches_test_case()
mini_batches = random_mini_batches(X_assess, Y_assess, mini_batch_size)
print ("shape of the 1st mini_batch_X: " + str(mini_batches[0][0].shape))
print ("shape of the 2nd mini_batch_X: " + str(mini_batches[1][0].shape))
print ("shape of the 3rd mini_batch_X: " + str(mini_batches[2][0].shape))
print ("shape of the 1st mini_batch_Y: " + str(mini_batches[0][1].shape))
print ("shape of the 2nd mini_batch_Y: " + str(mini_batches[1][1].shape))
print ("shape of the 3rd mini_batch_Y: " + str(mini_batches[2][1].shape))
print ("mini batch sanity check: " + str(mini_batches[0][0][0][0:3]))
print("=================================================")
结果是:
shape of the 1st mini_batch_X: (12288, 64)
shape of the 2nd mini_batch_X: (12288, 64)
shape of the 3rd mini_batch_X: (12288, 20)
shape of the 1st mini_batch_Y: (1, 64)
shape of the 2nd mini_batch_Y: (1, 64)
shape of the 3rd mini_batch_Y: (1, 20)
mini batch sanity check: [ 0.90085595 -0.7612069 0.2344157 ]
4. 这里我改变一下原来的代码顺序(注意,这一段应该放在最后,只能在预测函数前面)
1. 这里写一下model函数,就是最后预测函数调用的汇总函数,先看代码,然后再讲解注意的地方
#下面来看看这个model函数
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):
"""
3-layer neural network model which can be run in different optimizer modes.
Arguments:
X -- input data, of shape (2, number of examples)
Y -- true "label" vector (1 for blue dot / 0 for red dot), of shape (1, number of examples)
layers_dims -- python list, containing the size of each layer
learning_rate -- the learning rate, scalar.
mini_batch_size -- the size of a mini batch
beta -- Momentum hyperparameter
beta1 -- Exponential decay hyperparameter for the past gradients estimates
beta2 -- Exponential decay hyperparameter for the past squared gradients estimates
epsilon -- hyperparameter preventing division by zero in Adam updates
num_epochs -- number of epochs
print_cost -- True to print the cost every 1000 epochs
Returns:
parameters -- python dictionary containing your updated parameters
"""
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 the seed to reshuffle 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
没错,这个函数就更新参数用的,然后由于会用于三种方法,所以里面有选择语句(比如32到38行)。
另外,还需要注意的地方是,mini-batch的前向传播与反向传播(47到69行)。47行上方的mini-batchs参数的划分,然后对每一个batch循环来更新参数paramrter。
2. 然后记住,跑model函数之前需要先导入数据
#跑一下这个model函数
#先导入数据
train_X, train_Y = load_dataset()
3. 现在来看看普通的mini-batch算法,同样,这里我调换了一下顺序
其实就是调用之前写的函数(model),直接先上代码(注意,这里要先导入数据,上方model函数的后面写了导入代码)
#普通mini-batch下降
# train 3-layer model
layers_dims = [train_X.shape[0], 5, 2, 1]
parameters = model(train_X, train_Y, layers_dims, optimizer = "gd")
# Predict
predictions = predict(train_X, train_Y, parameters)
# Plot decision boundary
plt.title("Model with Gradient Descent optimization")
axes = plt.gca()
axes.set_xlim([-1.5,2.5])
axes.set_ylim([-1,1.5])
plot_decision_boundary(lambda x: predict_dec(parameters, x.T), train_X, train_Y)
print("=================================")
大家可以看到,就是调用model函数得到参数,然后调用predict函数来得到易看懂的结果,结果如下
Cost after epoch 0: 0.690736
Cost after epoch 1000: 0.685273
Cost after epoch 2000: 0.647072
Cost after epoch 3000: 0.619525
Cost after epoch 4000: 0.576584
Cost after epoch 5000: 0.607243
Cost after epoch 6000: 0.529403
Cost after epoch 7000: 0.460768
Cost after epoch 8000: 0.465586
Cost after epoch 9000: 0.464518
Accuracy: 0.796666666667
cost曲线为
然后我们来看看边界划分:
5. 现在我们开始写monmentum(动态梯度下降)算法
1.首先进行参数初始化
# GRADED FUNCTION: initialize_velocity
def initialize_velocity(parameters):
"""
Initializes the velocity as a python dictionary with:
- keys: "dW1", "db1", ..., "dWL", "dbL"
- values: numpy arrays of zeros of the same shape as the corresponding gradients/parameters.
Arguments:
parameters -- python dictionary containing your parameters.
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
Returns:
v -- python dictionary containing the current velocity.
v['dW' + str(l)] = velocity of dWl
v['db' + str(l)] = velocity of dbl
"""
L = len(parameters) // 2 # number of layers in the neural networks
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
没有什么惊奇的地方,初始化时v,b都为0(就不上输出结果了,一大堆0),如果要输出看看,代码是这样的
#输出看看效果
parameters = initialize_velocity_test_case()
v = initialize_velocity(parameters)
print("v[\"dW1\"] = " + str(v["dW1"]))
print("v[\"db1\"] = " + str(v["db1"]))
print("v[\"dW2\"] = " + str(v["dW2"]))
print("v[\"db2\"] = " + str(v["db2"]))
print("==================================")
2. 参数初始化完毕后,现在开始用momentum算法的更新参数W , b的值(注意,这里还有v的计算)
# GRADED FUNCTION: update_parameters_with_momentum
def update_parameters_with_momentum(parameters, grads, v, beta, learning_rate):
"""
Update parameters using Momentum
Arguments:
parameters -- python dictionary containing your parameters:
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
grads -- python dictionary containing your gradients for each parameters:
grads['dW' + str(l)] = dWl
grads['db' + str(l)] = dbl
v -- python dictionary containing the current velocity:
v['dW' + str(l)] = ...
v['db' + str(l)] = ...
beta -- the momentum hyperparameter, scalar
learning_rate -- the learning rate, scalar
Returns:
parameters -- python dictionary containing your updated parameters
v -- python dictionary containing your updated velocities
"""
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)] = parameters["W" + str(l + 1)] - learning_rate * v["dW" + str(l + 1)]
parameters["b" + str(l + 1)] = parameters["b" + str(l +1 )] - learning_rate * v["db" + str(l + 1)]
### END CODE HERE ###
return parameters, v
现在来看看执行效果
#现在来看看效果
parameters, grads, v = update_parameters_with_momentum_test_case()
parameters, v = update_parameters_with_momentum(parameters, grads, v, beta = 0.9, learning_rate = 0.01)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
print("v[\"dW1\"] = " + str(v["dW1"]))
print("v[\"db1\"] = " + str(v["db1"]))
print("v[\"dW2\"] = " + str(v["dW2"]))
print("v[\"db2\"] = " + str(v["db2"]))
#其实v["dW"]啥的,都是在一次次循环里更新的,,,确实就是只要初始化为0他的更新是和parameters里的W与b一起的
print("================================")
输出长这样:
W1 = [[ 1.62544598 -0.61290114 -0.52907334]
[-1.07347112 0.86450677 -2.30085497]]
b1 = [[ 1.74493465]
[-0.76027113]]
W2 = [[ 0.31930698 -0.24990073 1.4627996 ]
[-2.05974396 -0.32173003 -0.38320915]
[ 1.13444069 -1.0998786 -0.1713109 ]]
b2 = [[-0.87809283]
[ 0.04055394]
[ 0.58207317]]
v["dW1"] = [[-0.11006192 0.11447237 0.09015907]
[ 0.05024943 0.09008559 -0.06837279]]
v["db1"] = [[-0.01228902]
[-0.09357694]]
v["dW2"] = [[-0.02678881 0.05303555 -0.06916608]
[-0.03967535 -0.06871727 -0.08452056]
[-0.06712461 -0.00126646 -0.11173103]]
v["db2"] = [[ 0.02344157]
[ 0.16598022]
[ 0.07420442]]
3. 好了,现在开始用momentum的mini-batch梯度下降
代码如下:
# train 3-layer model
layers_dims = [train_X.shape[0], 5, 2, 1]
parameters = model(train_X, train_Y, layers_dims, beta = 0.9, optimizer = "momentum")
# Predict
predictions = predict(train_X, train_Y, parameters)
# Plot decision boundary
plt.title("Model with Momentum optimization")
axes = plt.gca()
axes.set_xlim([-1.5,2.5])
axes.set_ylim([-1,1.5])
plot_decision_boundary(lambda x: predict_dec(parameters, x.T), train_X, train_Y)
print("======================================")
输出长这样:
Cost after epoch 0: 0.690741
Cost after epoch 1000: 0.685341
Cost after epoch 2000: 0.647145
Cost after epoch 3000: 0.619594
Cost after epoch 4000: 0.576665
Cost after epoch 5000: 0.607324
Cost after epoch 6000: 0.529476
Cost after epoch 7000: 0.460936
Cost after epoch 8000: 0.465780
Cost after epoch 9000: 0.464740
Accuracy: 0.796666666667
cost曲线
然后现在看看边界划分
6. 接下来看Adam优化方法(则种方法像结合monmentum方法以及RMSprop方法,所以这里没有单独谈RMSprop方法)
1. 同样,先是初始化参数(全都为0)
# GRADED FUNCTION: initialize_adam
def initialize_adam(parameters):
"""
Initializes v and s as two python dictionaries with:
- keys: "dW1", "db1", ..., "dWL", "dbL"
- values: numpy arrays of zeros of the same shape as the corresponding gradients/parameters.
Arguments:
parameters -- python dictionary containing your parameters.
parameters["W" + str(l)] = Wl
parameters["b" + str(l)] = bl
Returns:
v -- python dictionary that will contain the exponentially weighted average of the gradient.
v["dW" + str(l)] = ...
v["db" + str(l)] = ...
s -- python dictionary that will contain the exponentially weighted average of the squared gradient.
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
和之前类似,输代码是(这里就不输出了,全是0):
#上面是为Adam算法进行了v["dW"],v["db"],s["dW"],s["sb"]的初始化
#来看看效果
parameters = initialize_adam_test_case()
v, s = initialize_adam(parameters)
print("v[\"dW1\"] = " + str(v["dW1"]))
print("v[\"db1\"] = " + str(v["db1"]))
print("v[\"dW2\"] = " + str(v["dW2"]))
print("v[\"db2\"] = " + str(v["db2"]))
print("s[\"dW1\"] = " + str(s["dW1"]))
print("s[\"db1\"] = " + str(s["db1"]))
print("s[\"dW2\"] = " + str(s["dW2"]))
print("s[\"db2\"] = " + str(s["db2"]))
print("==============================")
2. 接下来是更新Adam算法的参数
主要是注意s参数的更新,v的更新和之前的类似
# GRADED FUNCTION: update_parameters_with_adam
def update_parameters_with_adam(parameters, grads, v, s, t, learning_rate=0.01,
beta1=0.9, beta2=0.999, epsilon=1e-8):
"""
Update parameters using Adam
Arguments:
parameters -- python dictionary containing your parameters:
parameters['W' + str(l)] = Wl
parameters['b' + str(l)] = bl
grads -- python dictionary containing your gradients for each parameters:
grads['dW' + str(l)] = dWl
grads['db' + str(l)] = dbl
v -- Adam variable, moving average of the first gradient, python dictionary
s -- Adam variable, moving average of the squared gradient, python dictionary
learning_rate -- the learning rate, scalar.
beta1 -- Exponential decay hyperparameter for the first moment estimates
beta2 -- Exponential decay hyperparameter for the second moment estimates
epsilon -- hyperparameter preventing division by zero in Adam updates
Returns:
parameters -- python dictionary containing your updated parameters
v -- Adam variable, moving average of the first gradient, python dictionary
s -- Adam variable, moving average of the squared gradient, python dictionary
"""
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)
#下面进行偏差修正
v_corrected["dW" + str(l + 1)] = v["dW" + str(l + 1)] / (1 - beta1)
v_corrected["db" + str(l + 1)] = v["db" + str(l + 1)] / (1 - beta1)
# 这里有个疑问,和Ng课上讲的不太一样感觉,beta2不用该有一个t次方么?
### 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 - beta2)
s_corrected["db" + str(l + 1)] = s["db" + str(l + 1)] / (1 - beta2)
#这里有个疑问,和Ng课上讲的不太一样感觉,beta2不用该有一个t次方么?
### 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
另外说明一点,对于42,43,55,56行是在进行偏差修正。
还有就是,就像我57行中注释的一样,在课程中讲到过有一个beta2^t,但是这里却没有这个,我还没有找到为什么,但是由于课程中页提到,偏差修正很多时候不进行,对最后结果一般也没有太大影响,所以这里我貌似没有发现什么问题。
现在我们来看看检测代码:
#测试一下
parameters, grads, v, s = update_parameters_with_adam_test_case()
parameters, v, s = update_parameters_with_adam(parameters, grads, v, s, t = 2)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
print("v[\"dW1\"] = " + str(v["dW1"]))
print("v[\"db1\"] = " + str(v["db1"]))
print("v[\"dW2\"] = " + str(v["dW2"]))
print("v[\"db2\"] = " + str(v["db2"]))
print("s[\"dW1\"] = " + str(s["dW1"]))
print("s[\"db1\"] = " + str(s["db1"]))
print("s[\"dW2\"] = " + str(s["dW2"]))
print("s[\"db2\"] = " + str(s["db2"]))
print("=============================")
测试结果是这样:
W1 = [[ 1.63434536 -0.62175641 -0.53817175]
[-1.08296862 0.85540763 -2.2915387 ]]
b1 = [[ 1.75481176]
[-0.7512069 ]]
W2 = [[ 0.3290391 -0.25937038 1.47210794]
[-2.05014071 -0.3124172 -0.37405435]
[ 1.14376944 -1.08989128 -0.16242821]]
b2 = [[-0.88785842]
[ 0.03221375]
[ 0.57281521]]
v["dW1"] = [[-0.11006192 0.11447237 0.09015907]
[ 0.05024943 0.09008559 -0.06837279]]
v["db1"] = [[-0.01228902]
[-0.09357694]]
v["dW2"] = [[-0.02678881 0.05303555 -0.06916608]
[-0.03967535 -0.06871727 -0.08452056]
[-0.06712461 -0.00126646 -0.11173103]]
v["db2"] = [[ 0.02344157]
[ 0.16598022]
[ 0.07420442]]
s["dW1"] = [[ 0.00121136 0.00131039 0.00081287]
[ 0.0002525 0.00081154 0.00046748]]
s["db1"] = [[ 1.51020075e-05]
[ 8.75664434e-04]]
s["dW2"] = [[ 7.17640232e-05 2.81276921e-04 4.78394595e-04]
[ 1.57413361e-04 4.72206320e-04 7.14372576e-04]
[ 4.50571368e-04 1.60392066e-07 1.24838242e-03]]
s["db2"] = [[ 5.49507194e-05]
[ 2.75494327e-03]
[ 5.50629536e-04]]
3. 现在放大招,开始用Adma的mini-batch梯度下降(同样,不要忘记导入数据哦)
# train 3-layer model
layers_dims = [train_X.shape[0], 5, 2, 1]
parameters = model(train_X, train_Y, layers_dims, optimizer = "adam")
# Predict
predictions = predict(train_X, train_Y, parameters)
# Plot decision boundary
plt.title("Model with Adam optimization")
axes = plt.gca()
axes.set_xlim([-1.5,2.5])
axes.set_ylim([-1,1.5])
plot_decision_boundary(lambda x: predict_dec(parameters, x.T), train_X, train_Y)
结果是这样:
Cost after epoch 0: 0.690468
Cost after epoch 1000: 0.325328
Cost after epoch 2000: 0.223535
Cost after epoch 3000: 0.109833
Cost after epoch 4000: 0.140489
Cost after epoch 5000: 0.111570
Cost after epoch 6000: 0.128548
Cost after epoch 7000: 0.036306
Cost after epoch 8000: 0.128252
Cost after epoch 9000: 0.211592
Accuracy: 0.943333333333
cost曲线
边界图片
感叹一下,这个优化方法真的让分类效果好了不止一点点。
7. 总结一下:
三种方法,分类准确度一个比一个高,最后,Adam算法胜出,前两个都是:
0.796666666667
到了Adam算法,直接飙升到:
0.943333333333
可见优化算法不止对训练速度有大大的改善,还对分类效果有不小的影响。