python神经网络使用Keras构建RNN训练

Keras中构建RNN的重要函数

1、SimpleRNN

SimpleRNN用于在Keras中构建普通的简单RNN层，在使用前需要import。

from keras.layers import SimpleRNN

在实际使用时，需要用到几个参数。

model.add(
   SimpleRNN(
       batch_input_shape = (BATCH_SIZE,TIME_STEPS,INPUT_SIZE),
       output_dim = CELL_SIZE,
   )
)

其中，batch_input_shape代表RNN输入数据的shape，shape的内容分别是每一次训练使用的BATCH，TIME_STEPS表示这个RNN按顺序输入的时间点的数量，INPUT_SIZE表示每一个时间点的输入数据大小。
CELL_SIZE代表训练每一个时间点的神经元数量。

2、model.train_on_batch

与之前的训练CNN网络和普通分类网络不同，RNN网络在建立时就规定了batch_input_shape，所以训练的时候也需要一定量一定量的传入训练数据。
model.train_on_batch在使用前需要对数据进行处理。获取指定BATCH大小的训练集。

X_batch = X_train[index_start:index_start + BATCH_SIZE,:,:]
Y_batch = Y_train[index_start:index_start + BATCH_SIZE,:]
index_start += BATCH_SIZE

具体训练过程如下：

for i in range(500):
   X_batch = X_train[index_start:index_start + BATCH_SIZE,:,:]
   Y_batch = Y_train[index_start:index_start + BATCH_SIZE,:]
   index_start += BATCH_SIZE
   cost = model.train_on_batch(X_batch,Y_batch)
   if index_start >= X_train.shape[0]:
       index_start = 0
   if i％100 == 0:
       ## acc
       cost,accuracy = model.evaluate(X_test,Y_test,batch_size=50)
       ## W,b = model.layers[0].get_weights()
       print("accuracy:",accuracy)
       x = X_test[1].reshape(1,28,28)

全部代码

这是一个RNN神经网络的例子，用于识别手写体。

import numpy as np
from keras.models import Sequential
from keras.layers import SimpleRNN,Activation,Dense ## 全连接层
from keras.datasets import mnist
from keras.utils import np_utils
from keras.optimizers import Adam
TIME_STEPS = 28
INPUT_SIZE = 28
BATCH_SIZE = 50
index_start = 0
OUTPUT_SIZE = 10
CELL_SIZE = 75
LR = 1e-3
(X_train,Y_train),(X_test,Y_test) = mnist.load_data()
X_train = X_train.reshape(-1,28,28)/255
X_test = X_test.reshape(-1,28,28)/255
Y_train = np_utils.to_categorical(Y_train,num_classes= 10)
Y_test = np_utils.to_categorical(Y_test,num_classes= 10)
model = Sequential()
# conv1
model.add(
   SimpleRNN(
       batch_input_shape = (BATCH_SIZE,TIME_STEPS,INPUT_SIZE),
       output_dim = CELL_SIZE,
   )
)
model.add(Dense(OUTPUT_SIZE))
model.add(Activation("softmax"))
adam = Adam(LR)
## compile
model.compile(loss = 'categorical_crossentropy',optimizer = adam,metrics = ['accuracy'])
## tarin
for i in range(500):
   X_batch = X_train[index_start:index_start + BATCH_SIZE,:,:]
   Y_batch = Y_train[index_start:index_start + BATCH_SIZE,:]
   index_start += BATCH_SIZE
   cost = model.train_on_batch(X_batch,Y_batch)
   if index_start >= X_train.shape[0]:
       index_start = 0
   if i％100 == 0:
       ## acc
       cost,accuracy = model.evaluate(X_test,Y_test,batch_size=50)
       ## W,b = model.layers[0].get_weights()
       print("accuracy:",accuracy)

实验结果为：

10000/10000 [==============================] - 1s 147us/step
accuracy: 0.09329999938607215
…………………………
10000/10000 [==============================] - 1s 112us/step
accuracy: 0.9395000022649765
10000/10000 [==============================] - 1s 109us/step
accuracy: 0.9422999995946885
10000/10000 [==============================] - 1s 114us/step
accuracy: 0.9534000000357628
10000/10000 [==============================] - 1s 112us/step
accuracy: 0.9566000008583069
10000/10000 [==============================] - 1s 113us/step
accuracy: 0.950799999833107
10000/10000 [==============================] - 1s 116us/step
10000/10000 [==============================] - 1s 112us/step
accuracy: 0.9474999988079071
10000/10000 [==============================] - 1s 111us/step
accuracy: 0.9515000003576278
10000/10000 [==============================] - 1s 114us/step
accuracy: 0.9288999977707862
10000/10000 [==============================] - 1s 115us/step
accuracy: 0.9487999993562698

来源：https://blog.csdn.net/weixin_44791964/article/details/101609556