#!/usr/bin/env python
# coding: utf-8

# # 程序说明
# 名称：将Keras作为tensorflow的精简接口
# 
# 时间：2016年11月17日
# 
# 说明：该程序使用Keras方便的定义模型和接口，然后使用Tensorflow做训练。最终达到他们协同工作的一个状态。
# 
# 数据集：MNIST
# 
# [原文地址](http://keras-cn.readthedocs.io/en/latest/blog/keras_and_tensorflow/)
# 
# ![image](http://keras-cn.readthedocs.io/en/latest/images/keras-tensorflow-logo.jpg)

# ## 1.加载keras模块

# In[1]:


from __future__ import print_function
import numpy as np
np.random.seed(1337)  # for reproducibility


# In[2]:


from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD, Adam, RMSprop
from keras.utils import np_utils
from keras.objectives import categorical_crossentropy


# ### 加载Keras的后端和tensorflow

# In[ ]:


import tensorflow as tf
from keras import backend as K


# ## 2.变量初始化

# In[4]:


batch_size = 128 
nb_classes = 10
nb_epoch = 20 


# ## 3.准备数据

# In[5]:


# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')


# ### 转换类标号

# In[6]:


# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)


# ## 4.建立模型
# ### 使用Sequential（）

# In[7]:


model = Sequential()
model.add(Dense(512, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))


# ### 打印模型

# In[8]:


model.summary()


# ## 5.训练与评估

# In[ ]:





# In[ ]:





# In[ ]:





# In[10]:


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


# ### 迭代训练

# In[11]:


history = model.fit(X_train, Y_train,
                    batch_size=batch_size, nb_epoch=nb_epoch,
                    verbose=1, validation_data=(X_test, Y_test))


# ### 模型评估

# In[12]:


score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])


# In[ ]: