使用keras实现简单的前向全连接神经网络

转载的原博客地址如下：

http://machinelearningmastery.com/tutorial-first-neural-network-python-keras/

下面是对该博客的几个关键点的记录：

1、可以设置随机数种子的时候,建议设置随机数种子,方便结果的复现.

from keras.models import Sequential
from keras.layers import Dense
import numpy
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)

2、

toy 数据的地址如下：http://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes/pima-indians-diabetes.data

加载数据的代码：

# load pima indians dataset
dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

3、定义模型

# create model
model = Sequential()
model.add(Dense(12, input_dim=8, init='uniform', activation='relu'))
model.add(Dense(8, init='uniform', activation='relu'))
model.add(Dense(1, init='uniform', activation='sigmoid'))

说明：Dense是全连接网络,只有第一层需要设定输入层的结点个数,其他都不需要

4、编译模型,就是自动将我们定义的代码,使用后端的代码tensorflow或theano去实现

# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

5、训练模型

# Fit the model
model.fit(X, Y, nb_epoch=150, batch_size=10)

6、评估模型

# evaluate the model
scores = model.evaluate(X, Y)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

7、进行预测

# calculate predictions
predictions = model.predict(X)
# round predictions
rounded = [round(x) for x in predictions]
print(rounded)

=============================================================

完整代码如下：

# Create first network with Keras
from keras.models import Sequential
from keras.layers import Dense
import numpy
import sys
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load pima indians dataset
dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]
# create model
model = Sequential()
model.add(Dense(12, input_dim=8, init='normal', activation='relu'))
model.add(Dense(8, init='normal', activation='relu'))
model.add(Dense(1, init='normal', activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy','binary_crossentropy'])
# Fit the model
model.fit(X, Y, nb_epoch=150, batch_size=10,  verbose=2)
# evaluate the model
scores = model.evaluate(X, Y)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
# calculate predictions
predictions = model.predict(X)
#print predictions
# round predictions
rounded = [round(x) for x in predictions]
#print(rounded)