吴恩达《神经网络和深度学习》—用一层隐藏层的神经网络分类二维数据
※※※※※上一篇:【用神经网络思想实现逻辑回归】※※※※※下一篇:【构建深度神经网络】※※※※※
现在是时候建立你的第一个神经网络了,它将具有一层隐藏层。你将看到此模型与你使用逻辑回归实现的模型之间的巨大差异。
做完该作业将掌握的技能:
∙ \bullet ∙ 实现具有单个隐藏层的二分类神经网络
∙ \bullet ∙ 使用具有非线性激活函数的神经元,例如tanh
∙ \bullet ∙ 计算交叉熵损失
∙ \bullet ∙ 实现前向和后向传播
本文所使用的资料:【点击下载】,提取码:rc4u。请在开始之前下载好所需资料,然后将文件解压到你的代码文件同一级目录下,请确保你的代码那里有planar_utils.py
和testCases.py
文件。
1 安装包
让我们首先导入在作业过程中需要的所有软件包。
∙
\bullet
∙ numpy
:是Python科学计算的基本包。
∙
\bullet
∙ sklearn
:提供了用于数据挖掘和分析的简单有效的工具。
∙
\bullet
∙ matplotlib
:是一个著名的Python图形库。
∙
\bullet
∙ testCases
:提供了一些测试示例来评估函数的正确性,参见下载的资料或者在底部查看它的代码。
∙
\bullet
∙ planar_utils
:提供了在这个任务中使用的各种有用的功能,参见下载的资料或者在底部查看它的代码。
如果你没有以上的库,请自行安装,并且在需要时按如下方式加载到程序中。
# Package imports
import numpy as np
import matplotlib.pyplot as plt
from testCases import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
#%matplotlib inline #如果你使用用的是Jupyter Notebook的话请取消注释。
np.random.seed(1) #设置一个固定的随机种子,以保证接下来的步骤中我们的结果是一致的。
2 数据集
首先,让我们获取处理的数据集。以下代码会将flower
二分类数据集加载到变量
X
X
X 和
Y
Y
Y 中。
X, Y = load_planar_dataset()
把数据集加载完成了,然后使用matplotlib可视化数据集,代码如下:
【代码】:
# Visualize the data:
plt.scatter(X[0, :], X[1, :], c=Y.reshape(X[0,:].shape), s=40, cmap=plt.cm.Spectral)
【结果】:
数据看起来像是带有一些红色(标签 y y y = 0)和一些蓝色( y y y = 1)点的“花”。我们的目标是建立一个适合该数据的分类模型。现在,我们已经有了以下的东西:
∙
\bullet
∙
X
X
X:包含特征(
x
1
x1
x1,
x
2
x2
x2)的numpy数组(矩阵)
∙
\bullet
∙
Y
Y
Y:包含标签(红色:0,蓝色:1)的numpy数组(向量)
接着,让我们深入地了解一下我们的数据。
【代码】:
shape_X = X.shape
shape_Y = Y.shape
m = Y.shape[1] # 训练集里面的数量
print("X的维度为: " + str(shape_X))
print("Y的维度为: " + str(shape_Y))
print("数据集里面的数据有:" + str(m) + " 个")
【结果】:
X的维度为: (2, 400)
Y的维度为: (1, 400)
数据集里面的数据有:400 个
3 简单Logistic回归
在构建完整的神经网络之前,首先让我们看看逻辑回归在此问题上的表现。你可以使用sklearn
的内置函数来执行此操作。运行以下代码以在数据集上训练逻辑回归分类器。
【代码】:
# 训练逻辑回归分类器
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
【结果】:
这里会打印出以下的信息(不同的机器提示大同小异):
DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
y = column_or_1d(y, warn=True)
现在,可以运行下面的代码以绘制此模型的决策边界:
【代码】:
# 绘制逻辑回归分类器的决策边界
plot_decision_boundary(lambda x: clf.predict(x), X, Y) # 绘制决策边界
plt.title("Logistic Regression") # 图标题
LR_predictions = clf.predict(X.T) # 预测结果
print('逻辑回归的准确性: %d ' % float((np.dot(Y, LR_predictions) +
np.dot(1-Y, 1-LR_predictions))/float(Y.size)*100) +
'% ' + "(正确标记的数据点所占的百分比)")
【结果】:
逻辑回归的准确性: 47 % (正确标记的数据点所占的百分比)
可以看到,利用逻辑回归分类器得到的准确性只有47%,这主要是因为数据集不是线性可分类的,而逻辑回归分类器是线性分类器,因此逻辑回归效果不佳。 让我们试试是否神经网络会做得更好吧!
4 神经网络模型
从上面我们可以得知Logistic
回归不适用于flower数据集
。现在你将训练带有单个隐藏层的神经网络。
【模型】:
【数学原理】:
对于样本
x
(
i
)
x^{\left ( i \right )}
x(i),
z
[
1
]
(
i
)
=
W
[
1
]
x
(
i
)
+
b
[
1
]
(
i
)
(1)
z^{\left [ 1 \right ]\left ( i \right )} = W^{\left [ 1 \right ]}x^{\left ( i \right )}+b^{\left [ 1 \right ]\left ( i \right )} \tag{1}
z[1](i)=W[1]x(i)+b[1](i)(1)
a
[
1
]
(
i
)
=
t
a
n
h
(
z
[
1
]
(
i
)
)
(2)
a^{\left [ 1 \right ]\left ( i \right )}=tanh\left ( z^{\left [ 1 \right ]\left ( i \right )} \right )\tag{2}
a[1](i)=tanh(z[1](i))(2)
z
[
2
]
(
i
)
=
W
[
2
]
a
[
1
]
(
i
)
+
b
[
2
]
(
i
)
(3)
z^{\left [ 2 \right ]\left ( i \right )} = W^{\left [ 2 \right ]}a^{\left [ 1 \right ] \left ( i \right )}+b^{\left [ 2 \right ]\left ( i \right )} \tag{3}
z[2](i)=W[2]a[1](i)+b[2](i)(3)
y
^
(
i
)
=
a
[
2
]
(
i
)
=
σ
(
z
[
2
]
(
i
)
)
(4)
\hat{y}^{\left ( i \right )}=a^{\left [ 2 \right ]\left ( i \right )}=\sigma \left ( z^{\left [ 2 \right ]\left ( i \right )} \right ) \tag{4}
y^(i)=a[2](i)=σ(z[2](i))(4)
y
p
r
e
d
i
c
t
i
o
n
(
i
)
=
{
1
if
a
[
2
]
(
i
)
>
0.5
0
o
t
h
e
r
w
i
s
e
(5)
y_{prediction}^{\left ( i \right )}=\begin{cases} 1 & \text{ if } a^{\left [ 2 \right ]\left ( i \right )}>0.5 \\ 0 & otherwise \end{cases} \tag{5}
yprediction(i)={10 if a[2](i)>0.5otherwise(5)
根据所有的样本数据,可以根据下式计算损失
J
J
J:
J
=
−
1
m
∑
i
=
1
m
(
y
(
i
)
l
o
g
(
a
[
2
]
(
i
)
)
+
(
1
−
y
(
i
)
)
l
o
g
(
1
−
a
[
2
]
(
i
)
)
)
(6)
J = -\frac{1}{m}\sum_{i=1}^{m}\left ( y^{\left ( i \right )}log\left ( a^{\left [ 2 \right ]\left ( i \right )} \right ) + \left ( 1-y^{\left ( i \right )} \right )log\left ( 1-a^{\left [ 2 \right ]\left ( i \right )} \right ) \right ) \tag{6}
J=−m1i=1∑m(y(i)log(a[2](i))+(1−y(i))log(1−a[2](i)))(6)
【构建神经网络的步骤】:
1. 定义神经网络结构(输入单元数,隐藏单元数等)
2. 初始化模型的参数
3. 循环:
∙
\bullet
∙ 实现前向传播
∙
\bullet
∙ 计算成本
∙
\bullet
∙ 后向传播以获得梯度
∙
\bullet
∙ 更新参数(梯度下降)
我们通常会构建辅助函数来计算第1-3步,然后将它们合并为nn_model()
函数。一旦构建了nn_model()
并学习了正确的参数,就可以对新数据进行预测。
4.1 定义神经网络结构
首先,我们需要声明以下3个变量来定义神经网络的结构:
∙
\bullet
∙ n_x
:输入层的大小
∙
\bullet
∙ n_h
:隐藏层的大小(将其设置为4)
∙
\bullet
∙ n_y
:输出层的大小
【代码】:
def layer_sizes(X, Y):
"""
Arguments:
X -- input dataset of shape (input size, number of examples)
Y -- labels of shape (output size, number of examples)
Returns:
n_x -- the size of the input layer
n_h -- the size of the hidden layer
n_y -- the size of the output layer
"""
n_x = X.shape[0] # size of input layer
n_h = 4
n_y = Y.shape[0] # size of output layer
return n_x, n_h, n_y
【测试】:
# 测试layer_sizes
print("=========================测试layer_sizes=========================")
X_asses, Y_asses = layer_sizes_test_case()
(n_x, n_h, n_y) = layer_sizes(X_asses, Y_asses)
print("输入层的节点数量为: n_x = " + str(n_x))
print("隐藏层的节点数量为: n_h = " + str(n_h))
print("输出层的节点数量为: n_y = " + str(n_y))
【结果】:
=========================测试layer_sizes=========================
输入层的节点数量为: n_x = 5
隐藏层的节点数量为: n_h = 4
输出层的节点数量为: n_y = 2
4.2 初始化模型的参数
接下来,我们需要实现初始化模型参数的函数initialize_parameters()
。
【说明】:
∙
\bullet
∙ 请确保参数大小正确。 如果需要,也可参考上面的神经网络图。
∙
\bullet
∙ 使用随机值初始化权重矩阵:使用:np.random.randn(a,b)* 0.01
随机初始化维度为(a,b)
的矩阵。
∙
\bullet
∙ 将偏差向量初始化为零:使用:np.zeros((a,b))
初始化维度为(a,b)
零的矩阵。
【代码】:
def initialize_parameters(n_x, n_h, n_y):
"""
Argument:
n_x -- size of the input layer
n_h -- size of the hidden layer
n_y -- size of the output layer
Returns:
params -- python dictionary containing your parameters:
W1 -- weight matrix of shape (n_h, n_x)
b1 -- bias vector of shape (n_h, 1)
W2 -- weight matrix of shape (n_y, n_h)
b2 -- bias vector of shape (n_y, 1)
"""
np.random.seed(2) # 指定一个随机种子,以便你的输出与我们的一样。
W1 = np.random.randn(n_h, n_x) * 0.01
b1 = np.zeros((n_h, 1))
W2 = np.random.randn(n_y, n_h) * 0.01
b2 = np.zeros((n_y, 1))
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
【测试】:
# 测试initialize_parameters
print("=========================测试initialize_parameters=========================")
n_x, n_h, n_y = initialize_parameters_test_case()
parameters = initialize_parameters(n_x, n_h, n_y)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
【结果】:
=========================测试initialize_parameters=========================
W1 = [[-0.00416758 -0.00056267]
[-0.02136196 0.01640271]
[-0.01793436 -0.00841747]
[ 0.00502881 -0.01245288]]
b1 = [[0.]
[0.]
[0.]
[0.]]
W2 = [[-0.01057952 -0.00909008 0.00551454 0.02292208]]
b2 = [[0.]]
4.3 循环
4.3.1 前向传播
在这一步中,我们需要根据以下说明来实现前向传播函数forward_propagation()
。
∙
\bullet
∙ 可以使用sigmoid()
函数,也可以使用np.tanh()
函数。
∙
\bullet
∙ 使用parameters [“..”]
从字典 parameters
(这是initialize_parameters()
的输出)中检索出每个参数。
∙
\bullet
∙ 实现正向传播,计算
Z
[
1
]
,
A
[
1
]
,
Z
[
2
]
,
Z
[
2
]
Z^{\left [ 1 \right ]},\, A^{\left [ 1 \right ]},\,Z^{\left [ 2 \right ]},\,Z^{\left [ 2 \right ]}
Z[1],A[1],Z[2],Z[2](所有训练数据的预测结果向量)。
∙
\bullet
∙ 向后传播所需的值存储在cache
中, cache
将作为反向传播函数的输入。
【代码】:
def forward_propagation(X, parameters):
"""
Argument:
X -- input data of size (n_x, m)
parameters -- python dictionary containing your parameters (output of initialization function)
Returns:
A2 -- The sigmoid output of the second activation
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2"
"""
# Retrieve each parameter from the dictionary "parameters"
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Implement Forward Propagation to calculate A2 (probabilities)
Z1 = np.dot(W1, X) + b1
A1 = np.tanh(Z1)
Z2 = np.dot(W2, A1) + b2
A2 = sigmoid(Z2)
assert (A2.shape == (1, X.shape[1]))
cache = {"Z1": Z1,
"A1": A1,
"Z2": Z2,
"A2": A2}
return A2, cache
【测试】:
# 测试forward_propagation
print("=========================测试forward_propagation=========================")
X_assess, parameters = forward_propagation_test_case()
A2, cache = forward_propagation(X_assess, parameters)
print(np.mean(cache["Z1"]), np.mean(cache["A1"]), np.mean(cache["Z2"]), np.mean(cache["A2"]))
【结果】:
=========================测试forward_propagation=========================
-0.0004997557777419913 -0.0004969633532317802 0.0004381874509591466 0.500109546852431
4.3.2 计算成本
现在,我们已经计算了包含每个示例的
a
[
2
]
(
i
)
a^{\left [ 2 \right ]\left ( i \right )}
a[2](i) 的
A
[
2
]
A^{\left [ 2 \right ]}
A[2](在Python变量“A2”中),然后就可以根据公式(6)来实现成本函数compute_cost()
。
【说明】:
有很多的方法都可以计算交叉熵损失,比如对于下面的这个公式,
−
∑
i
=
1
m
y
(
i
)
l
o
g
(
a
[
2
]
(
i
)
)
-\sum_{i=1}^{m}y^{\left ( i \right )}log\left ( a^{\left [ 2 \right ]\left ( i \right )} \right )
−i=1∑my(i)log(a[2](i))
我们在python中可以这么实现:
logprobs = np.multiply(np.log(A2),Y)
cost = - np.sum(logprobs) # 不需要使用循环就可以直接算出来。
当然,我们也可以直接使用np.dot()
来进行计算。
【代码】:
def compute_cost(A2, Y, parameters):
"""
Computes the cross-entropy cost given in equation (13)
Arguments:
A2 -- The sigmoid output of the second activation, of shape (1, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
parameters -- python dictionary containing your parameters W1, b1, W2 and b2
Returns:
cost -- cross-entropy cost given equation (13)
"""
m = Y.shape[1] # number of example
# Compute the cross-entropy cost
logprobs = Y * np.log(A2) + (1 - Y) * np.log(1 - A2)
cost = -1 / m * np.sum(logprobs)
cost = np.squeeze(cost) # makes sure cost is the dimension we expect.
# E.g., turns [[17]] into 17
assert (isinstance(cost, float))
return cost
【测试】:
# 测试compute_cost
print("=========================测试compute_cost=========================")
A2, Y_assess, parameters = compute_cost_test_case()
print("cost = " + str(compute_cost(A2, Y_assess, parameters)))
【结果】:
=========================测试compute_cost=========================
cost = 0.6929198937761265
4.3.3 后向传播
接下来,就可以使用在正向传播期间计算的缓存,来实现后向传播backward_propagation()
。
【数学原理】:
反向传播通常是深度学习中最难(数学)的部分。为了帮助你更好地了解,你可以借助以下六个方程式来构建向量化实现。
【说明】:
∙
\bullet
∙
∗
\ast
∗ 表示对应元素相乘。
∙
\bullet
∙ 使用在深度学习中很常见的编码表示方法:
d
W
1
=
∂
J
∂
W
1
dW1=\frac{\partial J}{\partial W_1}
dW1=∂W1∂J
d
b
1
=
∂
J
∂
b
1
db1=\frac{\partial J}{\partial b_1}
db1=∂b1∂J
d
W
2
=
∂
J
∂
W
2
dW2=\frac{\partial J}{\partial W_2}
dW2=∂W2∂J
d
b
2
=
∂
J
∂
b
2
db2=\frac{\partial J}{\partial b_2}
db2=∂b2∂J
∙
\bullet
∙ 要计算
d
Z
1
dZ1
dZ1,首先需要计算
g
[
1
]
′
(
z
[
1
]
)
g^{\left [ 1 \right ]'}\left ( z^{[1]} \right )
g[1]′(z[1])。由于
g
[
1
]
(
⋅
)
g^{\left [ 1 \right ]}\left ( \cdot \right )
g[1](⋅) 是tanh
激活函数,因此如果
a
=
g
[
1
]
(
z
)
a = g^{\left [ 1 \right ]}\left ( z \right )
a=g[1](z),则
g
[
1
]
′
(
z
)
=
1
−
a
2
g^{\left [ 1 \right ]'}\left ( z \right ) = 1-a^{2}
g[1]′(z)=1−a2。所以,可以使用(1 - np.power(A1, 2))
计算
g
[
1
]
′
(
z
[
1
]
)
g^{\left [ 1 \right ]'}\left ( z^{[1]} \right )
g[1]′(z[1])。
【代码】:
def backward_propagation(parameters, cache, X, Y):
"""
Implement the backward propagation using the instructions above.
Arguments:
parameters -- python dictionary containing our parameters
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2".
X -- input data of shape (2, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
Returns:
grads -- python dictionary containing your gradients with respect to different parameters
"""
m = X.shape[1]
# First, retrieve W1 and W2 from the dictionary "parameters".
W1 = parameters["W1"]
W2 = parameters["W2"]
# Retrieve also A1 and A2 from dictionary "cache".
A1 = cache["A1"]
A2 = cache["A2"]
# Backward propagation: calculate dW1, db1, dW2, db2.
dZ2 = A2 - Y
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)
grads = {"dW1": dW1,
"db1": db1,
"dW2": dW2,
"db2": db2}
return grads
【测试】:
# 测试backward_propagation
print("=========================测试backward_propagation=========================")
parameters, cache, X_assess, Y_assess = backward_propagation_test_case()
grads = backward_propagation(parameters, cache, X_assess, Y_assess)
print("dW1 = " + str(grads["dW1"]))
print("db1 = " + str(grads["db1"]))
print("dW2 = " + str(grads["dW2"]))
print("db2 = " + str(grads["db2"]))
【结果】:
=========================测试backward_propagation=========================
dW1 = [[ 0.01018708 -0.00708701]
[ 0.00873447 -0.0060768 ]
[-0.00530847 0.00369379]
[-0.02206365 0.01535126]]
db1 = [[-0.00069728]
[-0.00060606]
[ 0.000364 ]
[ 0.00151207]]
dW2 = [[ 0.00363613 0.03153604 0.01162914 -0.01318316]]
db2 = [[0.06589489]]
4.3.4 使用梯度下降算法实现参数更新
现在,我们就可以利用梯度下降算法来实现参数的更新了。使用梯度下降,必须使用 ( d W 1 , d b 1 , d W 2 , d b 2 ) (dW1,db1,dW2,db2) (dW1,db1,dW2,db2)才能更新 ( W 1 , b 1 , W 2 , b 2 ) (W1,b1,W2,b2) (W1,b1,W2,b2)。一般的梯度下降规则为: θ = θ − α ∂ J ∂ θ \theta =\theta -\alpha\frac{\partial J}{\partial \theta } θ=θ−α∂θ∂J其中 α \alpha α 是学习率,而 θ \theta θ 代表一个参数。
下面两幅图展示了具有良好的学习速率(收敛)和较差的学习速率(发散)的梯度下降算法。
【代码】:
def update_parameters(parameters, grads, learning_rate=1.2):
"""
Updates parameters using the gradient descent update rule given above
Arguments:
parameters -- python dictionary containing your parameters
grads -- python dictionary containing your gradients
Returns:
parameters -- python dictionary containing your updated parameters
"""
# Retrieve each parameter from the dictionary "parameters"
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Retrieve each gradient from the dictionary "grads"
dW1 = grads["dW1"]
db1 = grads["db1"]
dW2 = grads["dW2"]
db2 = grads["db2"]
# Update rule for each parameter
W1 = W1 - learning_rate * dW1
b1 = b1 - learning_rate * db1
W2 = W2 - learning_rate * dW2
b2 = b2 - learning_rate * db2
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
【测试】:
# 测试update_parameters
print("=========================测试update_parameters=========================")
parameters, grads = update_parameters_test_case()
parameters = update_parameters(parameters, grads)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
【结果】:
=========================测试update_parameters=========================
W1 = [[-0.00643025 0.01936718]
[-0.02410458 0.03978052]
[-0.01653973 -0.02096177]
[ 0.01046864 -0.05990141]]
b1 = [[-1.02420756e-06]
[ 1.27373948e-05]
[ 8.32996807e-07]
[-3.20136836e-06]]
W2 = [[-0.01041081 -0.04463285 0.01758031 0.04747113]]
b2 = [[0.00010457]]
4.4 集成
最后,通过按照正确的顺序组合上述创建的函数就可以在nn_model()
函数中建立神经网络模型。
【代码】:
def nn_model(X, Y, n_h, num_iterations=10000, print_cost=False):
"""
Arguments:
X -- dataset of shape (2, number of examples)
Y -- labels of shape (1, number of examples)
n_h -- size of the hidden layer
num_iterations -- Number of iterations in gradient descent loop
print_cost -- if True, print the cost every 1000 iterations
Returns:
parameters -- parameters learnt by the model. They can then be used to predict.
"""
np.random.seed(3)
n_x = layer_sizes(X, Y)[0]
n_y = layer_sizes(X, Y)[2]
# Initialize parameters,
# then retrieve W1, b1, W2, b2. Inputs: "n_x, n_h, n_y". Outputs = "W1, b1, W2, b2, parameters".
parameters = initialize_parameters(n_x, n_h, n_y)
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Loop (gradient descent)
for i in range(0, num_iterations):
# Forward propagation. Inputs: "X, parameters". Outputs: "A2, cache".
A2, cache = forward_propagation(X, parameters)
# Cost function. Inputs: "A2, Y, parameters". Outputs: "cost".
cost = compute_cost(A2, Y, parameters)
# Backpropagation. Inputs: "parameters, cache, X, Y". Outputs: "grads".
grads = backward_propagation(parameters, cache, X, Y)
# Gradient descent parameter update. Inputs: "parameters, grads". Outputs: "parameters".
parameters = update_parameters(parameters, grads)
# Print the cost every 1000 iterations
if print_cost and i % 1000 == 0:
print("Cost after iteration %i: %f" % (i, cost))
return parameters
【测试】:
# 测试nn_model
print("=========================测试nn_model=========================")
X_assess, Y_assess = nn_model_test_case()
parameters = nn_model(X_assess, Y_assess, 4, num_iterations=10000, print_cost=False)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
【结果】:
=========================测试nn_model=========================
W1 = [[-4.18494714 5.33206444]
[-7.53806726 1.20753857]
[-4.19262445 5.32638718]
[ 7.53804391 -1.20755126]]
b1 = [[ 2.3293681 ]
[ 3.80995835]
[ 2.33015051]
[-3.80999435]]
W2 = [[-6033.82336187 -6008.1427588 -6033.08758194 6008.07912558]]
b2 = [[-52.67942084]]
4.5 预测
为了验证我们模型的准确性,我们可以根据nn_model()
函数输出的参数,利用正向传播来预测结果(参考公式(5))。
【代码】:
def predict(parameters, X):
"""
Using the learned parameters, predicts a class for each example in X
Arguments:
parameters -- python dictionary containing your parameters
X -- input data of size (n_x, m)
Returns
predictions -- vector of predictions of our model (red: 0 / blue: 1)
"""
# Computes probabilities using forward propagation, and classifies to 0/1 using 0.5 as the threshold.
A2, cache = forward_propagation(X, parameters)
predictions = np.round(A2)
return predictions
【测试】:
# 测试predict
print("=========================测试predict=========================")
parameters, X_assess = predict_test_case()
predictions = predict(parameters, X_assess)
print("预测的平均值 = " + str(np.mean(predictions)))
【结果】:
=========================测试predict=========================
预测的平均值 = 0.6666666666666666
至此,所有的工作都完成了,现在我们可以正式利用我们搭建的神经网络模型来训练flower
二分类数据集。
【代码】:
# Build a model with a n_h-dimensional hidden layer
parameters = nn_model(X, Y, n_h=4, num_iterations=10000, print_cost=True)
# Plot the decision boundary
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
plt.title("Decision Boundary for hidden layer size " + str(4))
plt.show()
【结果】:
Cost after iteration 0: 0.693048
Cost after iteration 1000: 0.288083
Cost after iteration 2000: 0.254385
Cost after iteration 3000: 0.233864
Cost after iteration 4000: 0.226792
Cost after iteration 5000: 0.222644
Cost after iteration 6000: 0.219731
Cost after iteration 7000: 0.217504
Cost after iteration 8000: 0.219449
Cost after iteration 9000: 0.218605
还可以利用以下代码来查看该训练好的神经网络模型的预测准确性。
【代码】:
# Print accuracy
predictions = predict(parameters, X)
print('Accuracy: %d' % float((np.dot(Y, predictions.T) + np.dot(1-Y, 1-predictions.T))/float(Y.size)*100) + '%')
【结果】:
Accuracy: 90%
与Logistic
回归相比,准确性确实更高。 该模型学习了flower的叶子图案!与逻辑回归不同,神经网络甚至能够学习非线性的决策边界。
4.6 调整隐藏层大小
我们上面的实验把隐藏层定为4个节点,现在我们更改隐藏层里面的节点数量,看一看节点数量是否会对结果造成影响。
【代码】:
plt.figure(figsize=(16, 32))
hidden_layer_sizes = [1, 2, 3, 4, 5, 10, 20]
for i, n_h in enumerate(hidden_layer_sizes):
plt.subplot(4, 2, i+1)
plt.title('Hidden Layer of size %d' % n_h)
parameters = nn_model(X, Y, n_h, num_iterations=5000)
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
predictions = predict(parameters, X)
accuracy = float((np.dot(Y, predictions.T) + np.dot(1-Y, 1-predictions.T))/float(Y.size)*100)
print("Accuracy for {} hidden units: {} %".format(n_h, accuracy))
【说明】:根据上述结果可以看出:
∙
\bullet
∙ 较大的模型(具有更多隐藏的单元)能够更好地拟合训练集,直到最终最大的模型过拟合数据为止。
∙
\bullet
∙ 隐藏层的最佳大小似乎在n_h = 5
左右。的确,此值似乎很好地拟合了数据,而又不会引起明显的过度拟合。
∙
\bullet
∙ 之后的教程还将学习正则化,帮助构建更大的模型(例如n_h = 50
)而不会过度拟合。
∙
\bullet
∙ 在上述代码中,plt.figure(figsize=(16, 32))
此行代码需要根据自己的电脑分辨率进行设置,否则画出来的图不好看。
5 模型在其他数据集上的性能
如果需要,可以为以下每个数据集重新运行构建的神经网络模型(除去数据集部分)。
首先,来看一下该模型在noisy_circles
数据集的运行效果(只需要把原来处理数据集的部分修改成以下代码就可以,不需要修改其他部分):
【代码】:
noisy_circles, noisy_moons, blobs, gaussian_quantiles, no_structure = load_extra_datasets()
datasets = {"noisy_circles": noisy_circles,
"noisy_moons": noisy_moons,
"blobs": blobs,
"gaussian_quantiles": gaussian_quantiles}
dataset = "noisy_circles" # 修改不同的数据集
X, Y = datasets[dataset]
X, Y = X.T, Y.reshape(1, Y.shape[0])
# make blobs binary
if dataset == "blobs":
Y = Y%2
【结果】:
X的维度为: (2, 200)
Y的维度为: (1, 200)
数据集里面的数据有:200 个
Cost after iteration 0: 0.693150
Cost after iteration 1000: 0.371229
Cost after iteration 2000: 0.360047
Cost after iteration 3000: 0.355231
Cost after iteration 4000: 0.352771
Cost after iteration 5000: 0.351263
Cost after iteration 6000: 0.351428
Cost after iteration 7000: 0.354861
Cost after iteration 8000: 0.354747
Cost after iteration 9000: 0.354317
Accuracy: 81%
接着,来看一下该模型在noisy_moons
数据集的运行效果:
【结果】:
X的维度为: (2, 200)
Y的维度为: (1, 200)
数据集里面的数据有:200 个
Cost after iteration 0: 0.693001
Cost after iteration 1000: 0.316565
Cost after iteration 2000: 0.317008
Cost after iteration 3000: 0.316195
Cost after iteration 4000: 0.099350
Cost after iteration 5000: 0.094745
Cost after iteration 6000: 0.093920
Cost after iteration 7000: 0.093484
Cost after iteration 8000: 0.093183
Cost after iteration 9000: 0.093618
Accuracy: 96%
然后,来看一下该模型在blobs
数据集的运行效果:
【结果】:
X的维度为: (2, 200)
Y的维度为: (1, 200)
数据集里面的数据有:200 个
Cost after iteration 0: 0.693527
Cost after iteration 1000: 0.324217
Cost after iteration 2000: 0.323287
Cost after iteration 3000: 0.323032
Cost after iteration 4000: 0.322912
Cost after iteration 5000: 0.322842
Cost after iteration 6000: 0.322796
Cost after iteration 7000: 0.322764
Cost after iteration 8000: 0.322739
Cost after iteration 9000: 0.322721
Accuracy: 83%
最后,来看一下该模型在gaussian_quantiles
数据集的运行效果:
【结果】:
X的维度为: (2, 200)
Y的维度为: (1, 200)
数据集里面的数据有:200 个
Cost after iteration 0: 0.693149
Cost after iteration 1000: 0.100718
Cost after iteration 2000: 0.077908
Cost after iteration 3000: 0.067646
Cost after iteration 4000: 0.062900
Cost after iteration 5000: 0.059589
Cost after iteration 6000: 0.057225
Cost after iteration 7000: 0.055425
Cost after iteration 8000: 0.054002
Cost after iteration 9000: 0.052850
Accuracy: 98%
综合上述可以看出,我们构建的单隐层神经网络模型对该四个数据集都能够训练出较好的结果,准确率相对较高。
6 完整代码
【nn_model.py】:
# -*- coding: utf-8 -*-
"""
Created on Wed Nov 21 14:00:00 2021
博客地址 :https://blog.csdn.net/qq_29923461?spm=1018.2226.3001.5343&type=blog
@author: 冷颜
"""
# Package imports
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from testCases import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets
np.random.seed(1) # 设置一个固定的随机种子,以保证接下来的步骤中我们的结果是一致的。
###########################################################
# 原始数据集处理
###########################################################
# Datasets
noisy_circles, noisy_moons, blobs, gaussian_quantiles, no_structure = load_extra_datasets()
datasets = {"noisy_circles": noisy_circles,
"noisy_moons": noisy_moons,
"blobs": blobs,
"gaussian_quantiles": gaussian_quantiles}
dataset = "gaussian_quantiles"
X, Y = datasets[dataset]
X, Y = X.T, Y.reshape(1, Y.shape[0])
# make blobs binary
if dataset == "blobs":
Y = Y%2
# 可视化数据
plt.scatter(X[0, :], X[1, :], c=Y.reshape(X[0, :].shape), s=40, cmap=plt.cm.Spectral)
plt.title("dataset: " + dataset)
plt.show()
shape_X = X.shape
shape_Y = Y.shape
m = Y.shape[1] # 训练集里面的数量
print("X的维度为: " + str(shape_X))
print("Y的维度为: " + str(shape_Y))
print("数据集里面的数据有:" + str(m) + " 个")
###########################################################
# 逻辑回归分类器
###########################################################
# 训练逻辑回归分类器
clf = sklearn.linear_model.LogisticRegressionCV()
clf.fit(X.T, Y.T)
## 绘制逻辑回归分类器的决策边界
# plot_decision_boundary(lambda x: clf.predict(x), X, Y) # 绘制决策边界
# plt.title("Logistic Regression") # 图标题
# LR_predictions = clf.predict(X.T) # 预测结果
# print('逻辑回归的准确性: %d ' % float((np.dot(Y, LR_predictions) +
# np.dot(1-Y, 1-LR_predictions))/float(Y.size)*100) +
# '% ' + "(正确标记的数据点所占的百分比)")
# plt.show()
###########################################################
# 定义神经网络结构:layer_sizes(X, Y)
###########################################################
def layer_sizes(X, Y):
"""
Arguments:
X -- input dataset of shape (input size, number of examples)
Y -- labels of shape (output size, number of examples)
Returns:
n_x -- the size of the input layer
n_h -- the size of the hidden layer
n_y -- the size of the output layer
"""
n_x = X.shape[0] # size of input layer
n_h = 4
n_y = Y.shape[0] # size of output layer
return n_x, n_h, n_y
###########################################################
# 初始化模型的参数:initialize_parameters(n_x, n_h, n_y)
###########################################################
def initialize_parameters(n_x, n_h, n_y):
"""
Argument:
n_x -- size of the input layer
n_h -- size of the hidden layer
n_y -- size of the output layer
Returns:
params -- python dictionary containing your parameters:
W1 -- weight matrix of shape (n_h, n_x)
b1 -- bias vector of shape (n_h, 1)
W2 -- weight matrix of shape (n_y, n_h)
b2 -- bias vector of shape (n_y, 1)
"""
np.random.seed(2) # 指定一个随机种子,以便你的输出与我们的一样。
W1 = np.random.randn(n_h, n_x) * 0.01
b1 = np.zeros((n_h, 1))
W2 = np.random.randn(n_y, n_h) * 0.01
b2 = np.zeros((n_y, 1))
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
###########################################################
# 前向传播:forward_propagation(X, parameters)
###########################################################
def forward_propagation(X, parameters):
"""
Argument:
X -- input data of size (n_x, m)
parameters -- python dictionary containing your parameters (output of initialization function)
Returns:
A2 -- The sigmoid output of the second activation
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2"
"""
# Retrieve each parameter from the dictionary "parameters"
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Implement Forward Propagation to calculate A2 (probabilities)
Z1 = np.dot(W1, X) + b1
A1 = np.tanh(Z1)
Z2 = np.dot(W2, A1) + b2
A2 = sigmoid(Z2)
assert (A2.shape == (1, X.shape[1]))
cache = {"Z1": Z1,
"A1": A1,
"Z2": Z2,
"A2": A2}
return A2, cache
###########################################################
# 计算成本:compute_cost(A2, Y, parameters)
###########################################################
def compute_cost(A2, Y, parameters):
"""
Computes the cross-entropy cost given in equation (13)
Arguments:
A2 -- The sigmoid output of the second activation, of shape (1, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
parameters -- python dictionary containing your parameters W1, b1, W2 and b2
Returns:
cost -- cross-entropy cost given equation (13)
"""
m = Y.shape[1] # number of example
# Compute the cross-entropy cost
logprobs = Y * np.log(A2) + (1 - Y) * np.log(1 - A2)
cost = -1 / m * np.sum(logprobs)
cost = np.squeeze(cost) # makes sure cost is the dimension we expect.
# E.g., turns [[17]] into 17
assert (isinstance(cost, float))
return cost
###########################################################
# 后向传播:backward_propagation(parameters, cache, X, Y)
###########################################################
def backward_propagation(parameters, cache, X, Y):
"""
Implement the backward propagation using the instructions above.
Arguments:
parameters -- python dictionary containing our parameters
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2".
X -- input data of shape (2, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
Returns:
grads -- python dictionary containing your gradients with respect to different parameters
"""
m = X.shape[1]
# First, retrieve W1 and W2 from the dictionary "parameters".
W1 = parameters["W1"]
W2 = parameters["W2"]
# Retrieve also A1 and A2 from dictionary "cache".
A1 = cache["A1"]
A2 = cache["A2"]
# Backward propagation: calculate dW1, db1, dW2, db2.
dZ2 = A2 - Y
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)
grads = {"dW1": dW1,
"db1": db1,
"dW2": dW2,
"db2": db2}
return grads
###########################################################
# 利用梯度下降算法更新参数:update_parameters(parameters, grads, learning_rate = 1.2)
###########################################################
def update_parameters(parameters, grads, learning_rate=1.2):
"""
Updates parameters using the gradient descent update rule given above
Arguments:
parameters -- python dictionary containing your parameters
grads -- python dictionary containing your gradients
Returns:
parameters -- python dictionary containing your updated parameters
"""
# Retrieve each parameter from the dictionary "parameters"
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Retrieve each gradient from the dictionary "grads"
dW1 = grads["dW1"]
db1 = grads["db1"]
dW2 = grads["dW2"]
db2 = grads["db2"]
# Update rule for each parameter
W1 = W1 - learning_rate * dW1
b1 = b1 - learning_rate * db1
W2 = W2 - learning_rate * dW2
b2 = b2 - learning_rate * db2
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
###########################################################
# 集成:nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False)
###########################################################
def nn_model(X, Y, n_h, num_iterations=10000, print_cost=False):
"""
Arguments:
X -- dataset of shape (2, number of examples)
Y -- labels of shape (1, number of examples)
n_h -- size of the hidden layer
num_iterations -- Number of iterations in gradient descent loop
print_cost -- if True, print the cost every 1000 iterations
Returns:
parameters -- parameters learnt by the model. They can then be used to predict.
"""
np.random.seed(3)
n_x = layer_sizes(X, Y)[0]
n_y = layer_sizes(X, Y)[2]
# Initialize parameters,
# then retrieve W1, b1, W2, b2. Inputs: "n_x, n_h, n_y". Outputs = "W1, b1, W2, b2, parameters".
parameters = initialize_parameters(n_x, n_h, n_y)
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
# Loop (gradient descent)
for i in range(0, num_iterations):
# Forward propagation. Inputs: "X, parameters". Outputs: "A2, cache".
A2, cache = forward_propagation(X, parameters)
# Cost function. Inputs: "A2, Y, parameters". Outputs: "cost".
cost = compute_cost(A2, Y, parameters)
# Backpropagation. Inputs: "parameters, cache, X, Y". Outputs: "grads".
grads = backward_propagation(parameters, cache, X, Y)
# Gradient descent parameter update. Inputs: "parameters, grads". Outputs: "parameters".
parameters = update_parameters(parameters, grads)
# Print the cost every 1000 iterations
if print_cost and i % 1000 == 0:
print("Cost after iteration %i: %f" % (i, cost))
return parameters
###########################################################
# 预测:predict(parameters, X)
###########################################################
def predict(parameters, X):
"""
Using the learned parameters, predicts a class for each example in X
Arguments:
parameters -- python dictionary containing your parameters
X -- input data of size (n_x, m)
Returns
predictions -- vector of predictions of our model (red: 0 / blue: 1)
"""
# Computes probabilities using forward propagation, and classifies to 0/1 using 0.5 as the threshold.
A2, cache = forward_propagation(X, parameters)
predictions = np.round(A2)
return predictions
# Build a model with a n_h-dimensional hidden layer
parameters = nn_model(X, Y, n_h=4, num_iterations=10000, print_cost=True)
# Plot the decision boundary
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
plt.title("dataset: " + dataset + "-Decision Boundary for hidden layer size " + str(4))
plt.show()
# Print accuracy
predictions = predict(parameters, X)
print('Accuracy: %d' % float((np.dot(Y, predictions.T) + np.dot(1-Y, 1-predictions.T))/float(Y.size)*100) + '%')
'''
plt.figure(figsize=(16, 32))
hidden_layer_sizes = [1, 2, 3, 4, 5, 10, 20]
for i, n_h in enumerate(hidden_layer_sizes):
plt.subplot(4, 2, i+1)
plt.title('Hidden Layer of size %d' % n_h)
parameters = nn_model(X, Y, n_h, num_iterations=5000)
plot_decision_boundary(lambda x: predict(parameters, x.T), X, Y)
predictions = predict(parameters, X)
accuracy = float((np.dot(Y, predictions.T) + np.dot(1-Y, 1-predictions.T))/float(Y.size)*100)
print("Accuracy for {} hidden units: {} %".format(n_h, accuracy))
plt.show()
'''
【planar_utils.py】:
# planar_utils.py
import matplotlib.pyplot as plt
import numpy as np
import sklearn
import sklearn.datasets
import sklearn.linear_model
def plot_decision_boundary(model, X, y):
# Set min and max values and give it some padding
x_min, x_max = X[0, :].min() - 1, X[0, :].max() + 1
y_min, y_max = X[1, :].min() - 1, X[1, :].max() + 1
h = 0.01
# Generate a grid of points with distance h between them
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
# Predict the function value for the whole grid
Z = model(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
# Plot the contour and training examples
plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)
plt.ylabel('x2')
plt.xlabel('x1')
plt.scatter(X[0, :], X[1, :], c=y, cmap=plt.cm.Spectral)
def sigmoid(x):
s = 1/(1+np.exp(-x))
return s
def load_planar_dataset():
np.random.seed(1)
m = 400 # number of examples
N = int(m/2) # number of points per class
D = 2 # dimensionality
X = np.zeros((m,D)) # data matrix where each row is a single example
Y = np.zeros((m,1), dtype='uint8') # labels vector (0 for red, 1 for blue)
a = 4 # maximum ray of the flower
for j in range(2):
ix = range(N*j,N*(j+1))
t = np.linspace(j*3.12,(j+1)*3.12,N) + np.random.randn(N)*0.2 # theta
r = a*np.sin(4*t) + np.random.randn(N)*0.2 # radius
X[ix] = np.c_[r*np.sin(t), r*np.cos(t)]
Y[ix] = j
X = X.T
Y = Y.T
return X, Y
def load_extra_datasets():
N = 200
noisy_circles = sklearn.datasets.make_circles(n_samples=N, factor=.5, noise=.3)
noisy_moons = sklearn.datasets.make_moons(n_samples=N, noise=.2)
blobs = sklearn.datasets.make_blobs(n_samples=N, random_state=5, n_features=2, centers=6)
gaussian_quantiles = sklearn.datasets.make_gaussian_quantiles(mean=None, cov=0.5, n_samples=N, n_features=2, n_classes=2, shuffle=True, random_state=None)
no_structure = np.random.rand(N, 2), np.random.rand(N, 2)
return noisy_circles, noisy_moons, blobs, gaussian_quantiles, no_structure
【testCases.py】:
# testCases.py
#-*- coding: UTF-8 -*-
"""
# WANGZHE12
"""
import numpy as np
def layer_sizes_test_case():
np.random.seed(1)
X_assess = np.random.randn(5, 3)
Y_assess = np.random.randn(2, 3)
return X_assess, Y_assess
def initialize_parameters_test_case():
n_x, n_h, n_y = 2, 4, 1
return n_x, n_h, n_y
def forward_propagation_test_case():
np.random.seed(1)
X_assess = np.random.randn(2, 3)
parameters = {'W1': np.array([[-0.00416758, -0.00056267],
[-0.02136196, 0.01640271],
[-0.01793436, -0.00841747],
[ 0.00502881, -0.01245288]]),
'W2': np.array([[-0.01057952, -0.00909008, 0.00551454, 0.02292208]]),
'b1': np.array([[ 0.],
[ 0.],
[ 0.],
[ 0.]]),
'b2': np.array([[ 0.]])}
return X_assess, parameters
def compute_cost_test_case():
np.random.seed(1)
Y_assess = np.random.randn(1, 3)
parameters = {'W1': np.array([[-0.00416758, -0.00056267],
[-0.02136196, 0.01640271],
[-0.01793436, -0.00841747],
[ 0.00502881, -0.01245288]]),
'W2': np.array([[-0.01057952, -0.00909008, 0.00551454, 0.02292208]]),
'b1': np.array([[ 0.],
[ 0.],
[ 0.],
[ 0.]]),
'b2': np.array([[ 0.]])}
a2 = (np.array([[ 0.5002307 , 0.49985831, 0.50023963]]))
return a2, Y_assess, parameters
def backward_propagation_test_case():
np.random.seed(1)
X_assess = np.random.randn(2, 3)
Y_assess = np.random.randn(1, 3)
parameters = {'W1': np.array([[-0.00416758, -0.00056267],
[-0.02136196, 0.01640271],
[-0.01793436, -0.00841747],
[ 0.00502881, -0.01245288]]),
'W2': np.array([[-0.01057952, -0.00909008, 0.00551454, 0.02292208]]),
'b1': np.array([[ 0.],
[ 0.],
[ 0.],
[ 0.]]),
'b2': np.array([[ 0.]])}
cache = {'A1': np.array([[-0.00616578, 0.0020626 , 0.00349619],
[-0.05225116, 0.02725659, -0.02646251],
[-0.02009721, 0.0036869 , 0.02883756],
[ 0.02152675, -0.01385234, 0.02599885]]),
'A2': np.array([[ 0.5002307 , 0.49985831, 0.50023963]]),
'Z1': np.array([[-0.00616586, 0.0020626 , 0.0034962 ],
[-0.05229879, 0.02726335, -0.02646869],
[-0.02009991, 0.00368692, 0.02884556],
[ 0.02153007, -0.01385322, 0.02600471]]),
'Z2': np.array([[ 0.00092281, -0.00056678, 0.00095853]])}
return parameters, cache, X_assess, Y_assess
def update_parameters_test_case():
parameters = {'W1': np.array([[-0.00615039, 0.0169021 ],
[-0.02311792, 0.03137121],
[-0.0169217 , -0.01752545],
[ 0.00935436, -0.05018221]]),
'W2': np.array([[-0.0104319 , -0.04019007, 0.01607211, 0.04440255]]),
'b1': np.array([[ -8.97523455e-07],
[ 8.15562092e-06],
[ 6.04810633e-07],
[ -2.54560700e-06]]),
'b2': np.array([[ 9.14954378e-05]])}
grads = {'dW1': np.array([[ 0.00023322, -0.00205423],
[ 0.00082222, -0.00700776],
[-0.00031831, 0.0028636 ],
[-0.00092857, 0.00809933]]),
'dW2': np.array([[ -1.75740039e-05, 3.70231337e-03, -1.25683095e-03,
-2.55715317e-03]]),
'db1': np.array([[ 1.05570087e-07],
[ -3.81814487e-06],
[ -1.90155145e-07],
[ 5.46467802e-07]]),
'db2': np.array([[ -1.08923140e-05]])}
return parameters, grads
def nn_model_test_case():
np.random.seed(1)
X_assess = np.random.randn(2, 3)
Y_assess = np.random.randn(1, 3)
return X_assess, Y_assess
def predict_test_case():
np.random.seed(1)
X_assess = np.random.randn(2, 3)
parameters = {'W1': np.array([[-0.00615039, 0.0169021 ],
[-0.02311792, 0.03137121],
[-0.0169217 , -0.01752545],
[ 0.00935436, -0.05018221]]),
'W2': np.array([[-0.0104319 , -0.04019007, 0.01607211, 0.04440255]]),
'b1': np.array([[ -8.97523455e-07],
[ 8.15562092e-06],
[ 6.04810633e-07],
[ -2.54560700e-06]]),
'b2': np.array([[ 9.14954378e-05]])}
return parameters, X_assess