keras搬砖系列-softmax(二)

再拖两天再补理论，实验室没有工程氛围啊。。。。自己来，不想考试，只想调参什么心理。。。

import numpy as np
np.random.seed(1337)
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Activation,Dropout
from keras.optimizers import RMSprop

(X_train,Y_train),(X_test,Y_test) = mnist.load_data()

#normal
X_train = X_train.reshape(X_train.shape[0],-1)/255
X_test = X_test.reshape(X_test.shape[0],-1)/255
Y_train = np_utils.to_categorical(Y_train,10)
Y_test = np_utils.to_categorical(Y_test,10)


## build model
model = Sequential()
model.add(Dense(128,input_dim=784))
model.add(Activation('relu'))
model.add(Dense(32))
model.add(Activation('relu'))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(10))
model.add(Activation('softmax'))

## optimizer
rmsprop = RMSprop(lr=0.01,rho=0.9,epsilon=1e-08,decay=0.0)

## compile
model.compile(optimizer='rmsprop',
              loss = 'categorical_crossentropy',
              metrics = ['accuracy'])

## fit
model.fit(X_train,Y_train,epochs=10,batch_size=256)
loss,accuracy = model.evaluate(X_test,Y_test)

print("the test loss:%s,the test accuracy:%s"%(loss,accuracy))

简单的几层，自己又随意添加了两层，发现没什么卵用，batch越小下降速率越慢，但是精确度好像有点高

如果没有过拟合不用使用Dropout，我好像正确率挺低的，学习率得自己调，一般来说用Adam优化器要好点。