循环神经网络（RNN）及长短时记忆网络（LSTM）

此篇文章是按我自己学习后的理解，RNN和LSTM概念啥的就不说了，主要将相关图文整理了一下。看起来可能不太连贯，主要作为一个概要笔记。
一，RNN
RNN结构示意图
这里写图片描述
RNN数据传输描述图

RNN与LSTM的cell单元结构比较
这里写图片描述

二，LSTM

LSTM整体结构图
这里写图片描述

控制参数，控制什么样的信息被保留，什么样的信息会被遗忘。
这里写图片描述

门单元，主要作用是让网络对信息进行选择
这里写图片描述

遗忘门
这里写图片描述

记忆门
这里写图片描述

更新细胞状态
这里写图片描述

输出门
这里写图片描述

三，LSTM实现手写字体识别
这里没有文字描述，主要是为了看图，理理LSTM数据传入的过程，加深理解。
图片来源“xxxx-RNN与LSTM网络原理进行唐诗生成视频课程 5”（出现第三方名称就发布不了了）
这里写图片描述

这里写图片描述

四，源代码
下面是用LSTM实现手写字体识别的源代码（参考网络的代码，进行了些许修改）

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# set random seed for comparing the two result calculations
tf.set_random_seed(1)

# this is data
mnist = input_data.read_data_sets("E:\sxl_Programs\Python\MNIST_data\MNIST_data", one_hot=True)

# hyperparameters  超参数
lr = 0.001        #学习率
training_iters = 10000   #训练轮数
batch_size = 200   

n_inputs = 28   # MNIST data input (img shape: 28*28)
n_steps = 28    # time steps
n_hidden_units = 128   # neurons in hidden layer
n_classes = 10      # MNIST classes (0-9 digits)

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

# Define weights
weights = {
    # (28, 128)
    'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
    # (128, 10)
    'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
    # (128, )
    'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
    # (10, )
    'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}


def RNN(X, weights, biases):
    # hidden layer for input to cell
    ########################################
    # transpose the inputs shape from
    # X ==> (128 batch * 28 steps, 28 inputs)
    X = tf.reshape(X, [-1, n_inputs])

    # into hidden
    # X_in = (128 batch * 28 steps, 128 hidden)
    X_in = tf.matmul(X, weights['in']) + biases['in']
    # X_in ==> (128 batch, 28 steps, 128 hidden)
    X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])

    # cell
    ##########################################
    # basic LSTM Cell.
    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
        cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
    else:
        cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units)
    # lstm cell is divided into two parts (c_state, h_state)
    init_state = cell.zero_state(batch_size, dtype=tf.float32)

    # You have 2 options for following step.
    # 1: tf.nn.rnn(cell, inputs);
    # 2: tf.nn.dynamic_rnn(cell, inputs).
    # If use option 1, you have to modified the shape of X_in, go and check out this:
    # https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
    # In here, we go for option 2.
    # dynamic_rnn receive Tensor (batch, steps, inputs) or (steps, batch, inputs) as X_in.
    # Make sure the time_major is changed accordingly.
    outputs, final_state = tf.nn.dynamic_rnn(cell, X_in, initial_state=init_state, time_major=False)

    # hidden layer for output as the final results
    #############################################
    # results = tf.matmul(final_state[1], weights['out']) + biases['out']

    # # or
    # unpack to list [(batch, outputs)..] * steps
    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
        outputs = tf.unpack(tf.transpose(outputs, [1, 0, 2]))    # states is the last outputs
    else:
        outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
    results = tf.matmul(outputs[-1], weights['out']) + biases['out']    # shape = (128, 10)\

    return results

pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
    # tf.initialize_all_variables() no long valid from
    # 2017-03-02 if using tensorflow >= 0.12
    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
        init = tf.initialize_all_variables()
    else:
        init = tf.global_variables_initializer()
    sess.run(init)
    step = 0
    while step < training_iters:
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
        sess.run([train_op], feed_dict={x: batch_xs,y: batch_ys})
        step += 1
        if step % 20 == 0:
            train_acc=sess.run(accuracy, feed_dict={x: batch_xs,y: batch_ys})
#             print(" Iter%d,Train accuracy: %.3f" % (step,train_acc))
            test_totalAccuracy=0.0
            irange=int(mnist.test.labels.shape[0]/batch_size)
            for i in range (irange):
                test_batch_xs, test_batch_ys = mnist.test.next_batch(batch_size)
                test_batch_xs = test_batch_xs.reshape([batch_size, n_steps, n_inputs])
                feeds = {x: test_batch_xs, y: test_batch_ys}
                test_acc = sess.run(accuracy, feed_dict=feeds)
                test_totalAccuracy+=test_acc
            test_totalAccuracy=test_totalAccuracy/(irange)  
            print("  Iter%d,Train accuracy: %.3f,Test accuracy: %.3f" % (step,train_acc,test_totalAccuracy))

五，运行结果：
这里写图片描述

六，相关文章
下面这个是个高手啊，写的文章质量都是上层的，有兴趣的可以去看看
https://blog.csdn.net/wangyangzhizhou/article/details/78878909
链接里有的文章：

LSTM神经网络

GRU神经网络

循环神经网络

卷积神经网络

深度学习的seq2seq模型

TensorFlow构建循环神经网络

TensorFlow实现seq2seq

谈谈谷歌word2vec的原理

如何用TensorFlow训练词向量

如何用TensorFlow训练聊天机器人（附github）

TensorFlow训练Logistic回归

TensorFlow训练单特征和多特征的线性回归

深度学习的Attention模型

循环神经网络（RNN）及长短时记忆网络（LSTM）

猜你喜欢