Keras实现RNN

Keras实现简单RNN

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.layers.recurrent import SimpleRNN
from keras.optimizers import Adam

#数据长度-一行有28个像素
input_size = 28
#序列长度-一行共有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('/home/n3/PycharmProjects/keras_study/mnist.npz')
x_train = x_train/255.0
x_test = x_test/255.0

#将label转换为 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)

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'))

#定义优化器
adam =Adam(lr=1e-4)

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('loss:',loss)
print('accuracy:',accuracy)

结果：

loss: 0.3319421031475067
accuracy: 0.902400016784668