第二次跟着 带有一个隐藏层的平面数据分类 把作业代码码了一遍,感觉思路更加清晰了。今天刚刚填报了国家保研系统中的基本信息,最近的学习状态很差,是时候沉下心来认真学习了。
main.py
import numpy
as np
import matplotlib
.pyplot
as plt
import sklearn
import sklearn
.datasets
import sklearn
.linear_model
from Deep_Learning
.testCases
import *
from Deep_Learning
.planar_utils
import plot_decision_boundary
, sigmoid
, load_planar_dataset
, load_extra_datasets
np
.random
.seed
(1)
X
, Y
= load_planar_dataset
()
plt
.scatter
(X
[0, :], X
[1, :], c
=np
.squeeze
(Y
), s
=40, cmap
=plt
.cm
.Spectral
)
plt
.show
()
shape_X
= X
.shape
shape_Y
= Y
.shape
m
= Y
.shape
[1]
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
))
clf
= sklearn
.linear_model
.LogisticRegressionCV
()
clf
.fit
(X
.T
, Y
.T
)
plot_decision_boundary
(lambda x
: clf
.predict
(x
), X
, np
.squeeze
(Y
))
plt
.title
("Logistic Regression")
LR_predictions
= clf
.predict
(X
.T
)
plt
.show
()
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)")
def layer_sizes(X
, Y
):
"""
:param X: -输入数据集,维度为(输入的数量,训练/测试的数量)
:param Y: -标签,维度为(输出的数量,训练/测试数量)
:return: n_x: -输入层的数量
n_h: -隐藏层的数量
n_y: -输出层的数量
"""
n_x
= X
.shape
[0]
n_h
= 4
n_y
= Y
.shape
[0]
return (n_x
, n_h
, n_y
)
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
))
def initialize_parameters(n_x
, n_h
, n_y
):
"""
:param n_x: -输入层节点的数量
:param n_h: -隐藏层节点的数量
:param n_y: -输出层节点的数量
:return: parameters -包含参数的字典
W1 -权重矩阵,维度为(n_h, n_x)
b1 -偏向量,维度为(n_h, 1)
W2 -权重矩阵,维度为(n_y, n_h)
b2 -偏向量,维度为(n_y, 1)
"""
np
.random
.seed
(2)
W1
= np
.random
.rand
(n_h
, n_x
) * 0.01
b1
= np
.zeros
(shape
=(n_h
, 1))
W2
= np
.random
.rand
(n_y
, n_h
) * 0.01
b2
= np
.zeros
(shape
=(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
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"]))
def forword_propagation(X
, parameters
):
"""
:param X: -维度为(n_x, m)的输入数据
:param parameters: -初始化函数(initialize_parameters)的输出
:return: A2 -使用sigmoid函数计算的第二次激活后的数值
cache -包含“Z1”,“A1”,“Z2”,“A2”的字典类型变量
"""
W1
= parameters
["W1"]
b1
= parameters
["b1"]
W2
= parameters
["W2"]
b2
= parameters
["b2"]
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
)
print("=======================测试forword_propagation=====================")
X_asses
, parameters
= forward_propagation_test_case
()
A2
, cache
= forword_propagation
(X_asses
, parameters
)
print(np
.mean
(cache
["Z1"]), np
.mean
(cache
["A1"]), np
.mean
(cache
["Z2"]), np
.mean
(cache
["A2"]))
def compute_cost(A2
, Y
, parameters
):
"""
:param A2: -使用sigmoid函数计算的第二次激活后的数值
:param Y: -"True"标签向量,维度为(1,数量)
:param parameters: -一个包含W1,b1,W2,b2的字典类型的变量
:return: cost -交叉熵成本
"""
m
= Y
.shape
[1]
W1
= parameters
["W1"]
W2
= parameters
["W2"]
logprobs
= np
.multiply
(np
.log
(A2
), Y
) + np
.multiply
((1 - Y
), np
.log
(1 - A2
))
np
.seterr
(divide
='ignore', invalid
='ignore')
cost
= - np
.sum(logprobs
) / m
cost
= float(np
.squeeze
(cost
))
assert (isinstance(cost
, float))
return cost
print("========================测试compute_cost======================")
A2
, Y_asses
, parameters
= compute_cost_test_case
()
print("cost = " + str(compute_cost
(A2
, Y_asses
, parameters
)))
def backward_propagation(parameters
, cache
, X
, Y
):
"""
:param parameters: -包含我们的参数的一个字典类型的变量
:param cache: -包含"Z1","A1","Z2","A2"的字典类型的变量
:param X: -输入数据,维度为(2,数量)
:param Y: -"True"标签向量,维度为(1,数量)
:return:grads -包含W和b的导数一个字典类型的变量
"""
m
= X
.shape
[1]
W1
= parameters
["W1"]
W2
= parameters
["W2"]
A1
= cache
["A1"]
A2
= cache
["A2"]
dZ2
= A2
- Y
dW2
= (1 / m
) * np
.dot
(dZ2
, A1
.T
)
db2
= (1 / m
) * np
.sum(dZ2
, axis
=1, keepdims
=True)
dZ1
= np
.multiply
(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
print("=======================测试backward_propagation======================")
parameters
, cache
, X_asses
, Y_asses
= backward_propagation_test_case
()
grads
= backward_propagation
(parameters
, cache
, X_asses
, Y_asses
)
print("dW1 = " + str(grads
["dW1"]))
print("db1 = " + str(grads
["db1"]))
print("dW2 = " + str(grads
["dW2"]))
print("db2 = " + str(grads
["db2"]))
def update_parameters(parameters
, grads
, learning_rate
=1.2):
"""
使用梯度下降更新规则更新参数
:param parameters: -包含参数的字典类型的变量
:param grads: -包含导数值的字典类型的变量
:param learning_rate: -学习速率
:return: parameters -包含更新参数的字典类型的变量
"""
W1
, W2
= parameters
["W1"], parameters
["W2"]
b1
, b2
= parameters
["b1"], parameters
["b2"]
dW1
, dW2
= grads
["dW1"], grads
["dW2"]
db1
, db2
= grads
["db1"], grads
["db2"]
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
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"]))
def nn_model(X
, Y
, n_h
, num_iterations
, print_cost
=False):
"""
:param X: -数据集,维度为(2,示例数)
:param Y: -标签,维度为(1,示例数)
:param n_h: -隐藏层的数量
:param num_iterations: -梯度下降循环中的迭代次数
:param print_cost: -如果为True,则每1000次迭代打印一次成本数值
:return: parameters -模型学习的参数,它们可以用来进行预测
"""
np
.random
.seed
(3)
n_x
= layer_sizes
(X
, Y
)[0]
n_y
= layer_sizes
(X
, Y
)[2]
parameters
= initialize_parameters
(n_x
, n_h
, n_y
)
W1
= parameters
["W1"]
b1
= parameters
["b1"]
W2
= parameters
["W2"]
b2
= parameters
["b2"]
for i
in range(num_iterations
):
A2
, cache
= forword_propagation
(X
, parameters
)
cost
= compute_cost
(A2
, Y
, parameters
)
grads
= backward_propagation
(parameters
, cache
, X
, Y
)
parameters
= update_parameters
(parameters
, grads
, learning_rate
=1.2)
if print_cost
:
if i
% 1000 == 0:
print("第", i
, "次循环,成本为:" + str(cost
))
return parameters
print("====================测试nn_model=======================")
X_asses
, Y_asses
= nn_model_test_case
()
parameters
= nn_model
(X_asses
, Y_asses
, 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"]))
def predict(parameters
, X
):
"""
使用学习的参数,为X中的每一个示例预测一个类
:param parameters: -包含参数的字典类型的变量
:param X: -输入数据(n_x, m)
:return: predictions -模型预测的向量(红色:0|蓝色:1)
"""
A2
, cache
= forword_propagation
(X
, parameters
)
predictions
= np
.round(A2
)
return predictions
print("=======================测试predict======================")
parameters
, X_asses
= predict_test_case
()
predictions
= predict
(parameters
, X_asses
)
print("预测的平均值 = " + str(np
.mean
(predictions
)))
parameters
= nn_model
(X
, Y
, n_h
=4, num_iterations
=10000, print_cost
=True)
plot_decision_boundary
(lambda x
: predict
(parameters
, x
.T
), X
, np
.squeeze
(Y
))
plt
.title
("Decision Boundary for hidden layer size " + str(4))
predictions
= predict
(parameters
, X
)
print('准确率:%d' % float((np
.dot
(Y
, predictions
.T
) + np
.dot
(1 - Y
, 1 - predictions
.T
)) / float(Y
.size
) * 100) + '%')
plt
.show
()
plt
.figure
(figsize
=(16, 32))
hidden_layer_sizes
= [1, 2, 3, 4, 5, 20, 50]
for i
, n_h
in enumerate(hidden_layer_sizes
):
plt
.subplot
(3, 3, 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("隐藏层的节点数量:{},准确率{}%".format(n_h
, accuracy
))
plt
.show
()
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
):
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
xx
, yy
= np
.meshgrid
(np
.arange
(x_min
, x_max
, h
), np
.arange
(y_min
, y_max
, h
))
Z
= model
(np
.c_
[xx
.ravel
(), yy
.ravel
()])
Z
= Z
.reshape
(xx
.shape
)
plt
.contourf
(xx
, yy
, Z
, cmap
=plt
.cm
.Spectral
)
plt
.ylabel
('x2')
plt
.xlabel
('x1')
plt
.scatter
(X
[0, :], X
[1, :], c
=np
.squeeze
(y
), cmap
=plt
.cm
.Spectral
)
def sigmoid(x
):
"""
当x是一个非常小的负数时,exp(-x)会过大,导致溢出,下面进行优化:
原式分子分母同乘exp(x)这个很小的数,可以防止数据溢出
"""
s
= 1 / (1 + np
.exp
(-x
))
return s
def load_planar_dataset():
np
.random
.seed
(1)
m
= 400
N
= int(m
/2)
D
= 2
X
= np
.zeros
((m
,D
))
Y
= np
.zeros
((m
,1), dtype
='uint8')
a
= 4
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
r
= a
*np
.sin
(4*t
) + np
.random
.randn
(N
)*0.2
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
"""
# 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
运行结果
X的维度为:
(2, 400)
Y的维度为:
(1, 400)
数据集里面的数据有:
400
F
:\Python\lib\site
-packages\sklearn\utils\validation
.py
:73: 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
().
return f
(**kwargs
)
逻辑回归的准确性:
47%(正确标记的数据点所占的百分比
)
========================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
=====================测试initialize_parameters
=========================
W1
= [[0.00435995 0.00025926]
[0.00549662 0.00435322]
[0.00420368 0.00330335]
[0.00204649 0.00619271]]
b1
= [[0.]
[0.]
[0.]
[0.]]
W2
= [[0.00299655 0.00266827 0.00621134 0.00529142]]
b2
= [[0.]]
=======================测试forword_propagation
=====================
-0.0004997557777419913 -0.0004969633532317802 0.0004381874509591466 0.500109546852431
========================测试compute_cost
======================
cost
= 0.6929198937761266
=======================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]]
======================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]]
====================测试nn_model
=======================
G
:\Project\PYTHON\Demo01\Deep_Learning\planar_utils
.py
:33: RuntimeWarning
: overflow encountered
in exp
s
= 1 / (1 + np
.exp
(-x
))
W1
= [[ 7.52965472 -1.24309301]
[ 4.21291395 -5.31399817]
[ 7.52966135 -1.2431499 ]
[ 4.21397291 -5.31333161]]
b1
= [[-3.79468532]
[-2.32838083]
[-3.79485646]
[-2.3283009 ]]
W2
= [[6006.88570125 6032.88338564 6007.41279754 6032.66790904]]
b2
= [[-53.17690741]]
=======================测试predict
======================
预测的平均值
= 0.6666666666666666
第
0 次循环,成本为:
0.6931586620054873
第
1000 次循环,成本为:
0.289307766073059
第
2000 次循环,成本为:
0.2738595561686524
第
3000 次循环,成本为:
0.238115797061788
第
4000 次循环,成本为:
0.22810205919496226
第
5000 次循环,成本为:
0.22331808633565126
第
6000 次循环,成本为:
0.220192917928194
第
7000 次循环,成本为:
0.21786964182913665
第
8000 次循环,成本为:
0.21603567135242685
第
9000 次循环,成本为:
0.21863707045894862
准确率:
90%
隐藏层的节点数量:
1,准确率
67.5%
隐藏层的节点数量:
2,准确率
67.25%
隐藏层的节点数量:
3,准确率
90.75%
隐藏层的节点数量:
4,准确率
90.75%
隐藏层的节点数量:
5,准确率
91.25%
隐藏层的节点数量:
20,准确率
90.0%
隐藏层的节点数量:
50,准确率
91.0%
依次显示的图片
原始数据集: 简单逻辑回归分类: 四个隐藏层的神经网络分类结果: 不同隐藏层的神经网络分类结果:
目前仍然存在的问题:
sigmoid函数需要优化
RuntimeWarning: overflow encountered in exp s = 1 / (1 + np.exp(-x))
代码存在警告,但可以正常运行
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(). return f(**kwargs)