神经网络学习小记录8——利用Keras进行简单RNN网络构建

谁借莪１个温暖的怀抱￠ 2023-08-17 16:22 110阅读 0赞

### 神经网络学习小记录8——利用Keras进行简单RNN网络构建 ###

*  学习前言
 *  Keras中构建RNN的重要函数
 *   *  1、SimpleRNN
     *  2、model.train\_on\_batch
 *  全部代码

# 学习前言 #

还要会RNN噢。  
![在这里插入图片描述][20190723165901974.jpg_pic_center]

# 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。（源自[莫烦Python][Python]）

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

**有不懂的朋友可以评论询问噢。**

[20190723165901974.jpg_pic_center]: /images/20230810/ad6a3d0c258a4faeacb185ae7ca0aef2.png
[Python]: https://morvanzhou.github.io/tutorials/machine-learning/keras/2-4-RNN-classifier/