Keras 回歸 擬合 收集

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

案例1

from keras.models import Sequential
from keras.layers import Dense, LSTM, Activation
from keras.optimizers import adam, rmsprop, adadelta
import numpy as np
import matplotlib.pyplot as plt
#construct model
models = Sequential()
models.add(Dense(100, init='uniform',activation='relu' ,input_dim=1))
models.add(Dense(50, activation='relu'))
models.add(Dense(1,activation='tanh'))
adamoptimizer = adam(lr=0.001, beta_1=0.9, beta_2=0.999, decay=0.00001)
models.compile(optimizer='rmsprop', loss='mse',metrics=["accuracy"] )

#train data
dataX = np.linspace(-2 * np.pi,2 * np.pi, 1000)
dataX = np.reshape(dataX, [dataX.__len__(), 1])
noise = np.random.rand(dataX.__len__(), 1) * 0.1
dataY = np.sin(dataX) + noise

models.fit(dataX, dataY, epochs=100, batch_size=10, shuffle=True, verbose = 1)
predictY = models.predict(dataX, batch_size=1)
score = models.evaluate(dataX, dataY, batch_size=10)

print(score)
#plot
fig, ax = plt.subplots()
ax.plot(dataX, dataY, 'b-')
ax.plot(dataX, predictY, 'r.',)

ax.set(xlabel="x", ylabel="y=f(x)", title="y = sin(x),red:predict data,bule:true data")
ax.grid(True)

plt.show()

案例2：

import numpy as np

import random
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense,Activation
from keras.optimizers import Adam,SGD

X = np.linspace(1,20,1000)
X = X[:,np.newaxis]
y = np.sin(X) + np.random.normal(0,0.08,(1000,1))
min_max_scaler = MinMaxScaler((0,1))
y_train = min_max_scaler.fit_transform(y)
x_train = min_max_scaler.fit_transform(X)

model1=Sequential()
model1.add(Dense(1000,input_dim = 1))
model1.add(Activation('relu'))
model1.add(Dense(1))
model1.add(Activation('sigmoid'))
adam = Adam(lr = 0.001)
sgd = SGD(lr = 0.1,decay=12-5,momentum=0.9)
model1.compile(optimizer = adam,loss = 'mse')
print('-------------training--------------')
model1.fit(x_train,y_train,batch_size= 12,nb_epoch = 500,shuffle=True)
Y_train_pred=model1.predict(x_train)
plt.scatter(x_train,y_train)
plt.plot(x_train,Y_train_pred,'r-')
plt.show()

案例3

#加激活函數的方法2：model.add(Dense(units=10,input_dim=1,activation=' '))
from keras.optimizers import SGD
from keras.layers import Dense,Activation
#構建一個順序模型
model=Sequential()

#在模型中添加一個全連接層
#units是輸出維度,input_dim是輸入維度(shift+兩次tab查看函數參數)
#輸入1個神經元,隱藏層10個神經元,輸出層1個神經元
model.add(Dense(units=10,input_dim=1,activation='relu'))   #增加非線性激活函數
model.add(Dense(units=1,activation='relu'))   #默認連接上一層input_dim=10

#定義優化算法(修改學習率)
defsgd=SGD(lr=0.3)

#編譯模型
model.compile(optimizer=defsgd,loss='mse')   #optimizer參數設置優化器,loss設置目標函數

#訓練模型
for step in range(3001):
    #每次訓練一個批次
    cost=model.train_on_batch(x_data,y_data)
    #每500個batch打印一個cost值
    if step%500==0:
        print('cost:',cost)

#打印權值和偏置值
W,b=model.layers[0].get_weights()   #layers[0]只有一個網絡層
print('W:',W,'b:',b)

#x_data輸入網絡中，得到預測值y_pred
y_pred=model.predict(x_data)

plt.scatter(x_data,y_data)

plt.plot(x_data,y_pred,'r-',lw=3)
plt.show()

案例4：

#加激活函數的方法1：mode.add(Activation(''))
from keras.optimizers import SGD
from keras.layers import Dense,Activation
import numpy as np

np.random.seed(0)
x_data=np.linspace(-0.5,0.5,200)
noise=np.random.normal(0,0.02,x_data.shape)
y_data=np.square(x_data)+noise

#構建一個順序模型
model=Sequential()

#在模型中添加一個全連接層
#units是輸出維度,input_dim是輸入維度(shift+兩次tab查看函數參數)
#輸入1個神經元,隱藏層10個神經元,輸出層1個神經元
model.add(Dense(units=10,input_dim=1))
model.add(Activation('tanh'))   #增加非線性激活函數
model.add(Dense(units=1))   #默認連接上一層input_dim=10
model.add(Activation('tanh'))

#定義優化算法(修改學習率)
defsgd=SGD(lr=0.3)

#編譯模型
model.compile(optimizer=defsgd,loss='mse')   #optimizer參數設置優化器,loss設置目標函數

#訓練模型
for step in range(3001):
    #每次訓練一個批次
    cost=model.train_on_batch(x_data,y_data)
    #每500個batch打印一個cost值
    if step%500==0:
        print('cost:',cost)

#打印權值和偏置值
W,b=model.layers[0].get_weights()   #layers[0]只有一個網絡層
print('W:',W,'b:',b)

#x_data輸入網絡中，得到預測值y_pred
y_pred=model.predict(x_data)

plt.scatter(x_data,y_data)

plt.plot(x_data,y_pred,'r-',lw=3)
plt.show()

案列5

import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam

np.random.seed(0)
points = 500
X = np.linspace(-3, 3, points)
y = np.sin(X) + np.random.uniform(-0.5, 0.5, points)


model = Sequential()
model.add(Dense(50, activation='sigmoid', input_dim=1))
model.add(Dense(30, activation='sigmoid'))
model.add(Dense(1))
adam = Adam(lr=0.01)
model.compile(loss='mse', optimizer=adam)
model.fit(X, y, epochs=50)

predictions = model.predict(X)
plt.scatter(X, y)
plt.plot(X, predictions, 'ro')
plt.show()

案列6：

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
x = list(np.arange(0,4,0.1))
#給3次多項式添加噪音
y = list(map(lambda val: val**3*3 + np.random.random()*20 , x) )

plt.scatter(x, y)

#指明用3次多項式匹配
w = np.polyfit (x, y, 3)
fn = np.poly1d(w)

#打印適配出來的參數和函數
print(w)
print(fn)

plt.plot(x, fn(x))

 

 

 

案列7 

 

 1 %matplotlib inline
 2 import matplotlib.pyplot as plt 3 from keras.datasets import mnist 4 from keras.models import Sequential 5 from keras.layers.core import Dense, Activation 6 from keras.layers.advanced_activations import LeakyReLU, PReLU 7 from keras.optimizers import SGD 8 9 x = list(np.arange(0,4,0.1)) 10 #給3次多項式添加噪音 11 y = list(map(lambda val: val**3*3 + np.random.random()*20 , x) ) 12 13 model = Sequential() 14 #神經元個數越多,效果會越好,收斂越快,太少的話難以收斂到所需曲線 15 model.add(Dense(100, input_shape=(1,))) 16 17 #Relu,得到的是一條橫線 18 #Tanh,稍稍好於Relu,但是擬合的不夠 19 #sigmoid, 只要神經元個數足夠(50+),訓練1000輪以上,就能達到比較好的效果 20 model.add(Activation('sigmoid')) 21 #model.add(LeakyReLU(alpha=0.01)) 22 #model.add(Dense(3)) 23 24 model.add(Dense(1)) 25 model.compile(optimizer="sgd", loss="mse") 26 model.fit(x, y, epochs=2000, verbose=0) 27 28 print(type(fn(3))) 29 print(fn(1)) 30 print(fn(3)) 31 32 plt.scatter(x, y) 33 plt.plot(x, model.predict(x))