keras 9_RNN

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

# 数据长度一行有28个像素
input_size = 28
# 数据长度一共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

# 将数据集标签转换为one-hot编码的格式
y_train = np_utils.to_categorical(y_train, num_classes=10)
y_test = np_utils.to_categorical(y_test, num_classes=10)

# 创建网络模型
model = Sequential()

# 循环神经网络
model.add(SimpleRNN(
    units=cell_size,    # 输出
    input_shape=(time_steps, input_size),  # 输入
))

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

# 优化器
adam = Adam(lr=0.001)

# 编译网络
model.compile(optimizer=adam,loss="categorical_crossentropy",metrics=["accuracy"])

# 训练模型
model.fit(x_train,y_train,batch_size=32,epochs=10)

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