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

# # 程序说明
# 时间：2016年11月16日
# 
# 说明：该程序是一个包含LSTM的神经网络。
# 
# 数据集：MNIST

# ## 1.加载keras模块

# In[1]:


from keras.models import Sequential
from keras.layers import LSTM, Dense
from keras.datasets import mnist
from keras.utils import np_utils
from keras import initializations

def init_weights(shape, name=None):
    return initializations.normal(shape, scale=0.01, name=name)


# #### 如需绘制模型请加载plot

# In[2]:


from keras.utils.visualize_util import plot


# ## 2.变量初始化

# In[3]:


# Hyper parameters
batch_size = 128
nb_epoch = 10

# Parameters for MNIST dataset
img_rows, img_cols = 28, 28
nb_classes = 10

# Parameters for LSTM network
nb_lstm_outputs = 30
nb_time_steps = img_rows
dim_input_vector = img_cols


# ## 3.准备数据

# In[4]:


# Load MNIST dataset
(X_train, y_train), (X_test, y_test) = mnist.load_data()
print('X_train original shape:', X_train.shape)
input_shape = (nb_time_steps, dim_input_vector)

X_train = X_train.astype('float32') / 255.
X_test = X_test.astype('float32') / 255.
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')


# ## 4.建立模型
# ### 使用Sequential（）

# In[5]:


# Build LSTM network
model = Sequential()
model.add(LSTM(nb_lstm_outputs, input_shape=input_shape))
model.add(Dense(nb_classes, activation='softmax', init=init_weights))


# ### 打印模型

# In[6]:


model.summary()


# ### 绘制模型结构图，并保存成图片

# In[7]:


plot(model, to_file='lstm_model.png')


# #### 显示绘制的图片
# ![image](http://p1.bqimg.com/4851/08854414148a36b0.png)

# ## 5.训练与评估
# ### 编译模型

# In[8]:


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


# ### 迭代训练

# In[9]:


history = model.fit(X_train, Y_train, nb_epoch=nb_epoch, batch_size=batch_size, shuffle=True, verbose=1)


# ### 模型评估

# In[10]:


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


# In[ ]: