RNN应用 和 保存 模型载入

import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam
from keras.layers.recurrent import SimpleRNN # 最简单的RNN

# 数据长度 - 一行有28个像素
input_size = 28
# 序列长度 - 一共有28行
time_steps = 28
# 隐藏层cell个数
cell_size = 50

# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000,28,28)
x_train = x_train/255.0
x_test = x_test/255.0
# 换one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)

# 创建模型
model = Sequential()

# 循环神经网络  定义一个循环神经网络
model.add(SimpleRNN(
    units = cell_size, #这个是输出，输出到50个cell
    input_shape = (time_steps,input_size) # 这个是输入
))

# 输出层
model.add(Dense(10,activation='softmax'))

# 定义优化器
adam = Adam(lr=1e-4)

# 定义优化器，loss function，训练过程中计算准确率
model.compile(optimizer=adam,loss='categorical_crossentropy',metrics=['accuracy'])

# 训练模型
model.fit(x_train,y_train,batch_size=64,epochs=10)

# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)

print('\ntest loss',loss)
print('test accuracy',accuracy)

# 保存模型
model.save('model.h5') # HDF5文件,pip install h5py

模型载入（在我的电脑上面有点问题 没有解决）

import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam

# 导入模型的包
from keras.models import load_model

# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000,28,28)
print('x_shape:',x_train.shape)
# (60000)
print('y_shape:',y_train.shape)
# (60000,28,28)->(60000,784)
x_train = x_train.reshape(x_train.shape[0],-1)/255.0
x_test = x_test.reshape(x_test.shape[0],-1)/255.0
# 换one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)

# 载入模型 是训练过的模型
model = load_model('model.h5')

# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)

print('\ntest loss',loss)
print('accuracy',accuracy)

# 训练模型
model.fit(x_train,y_train,batch_size=64,epochs=2)

# 评估模型
loss,accuracy = model.evaluate(x_test,y_test)

print('\ntest loss',loss)
print('accuracy',accuracy)