Tensorflow-LSTMRNN例子

使用Rnn预测一段波形的序列

导入模块

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.contrib import rnn

设置参数

batch_start = 0 #建立batch_data 的索引
time_steps = 20 #反向传播通过时间的time_steps
batch_size = 50
training_steps = 200
input_size = 1 #sin 数据输入 size
output_size = 1 #cos 数据输出 size
cell_size = 10 #RNN的隐藏单位的大小
learning_rate = 0.001 # 学习率

生成数据

def get_batch():    global batch_start,time_steps    # sx ==>(50batch, 20steps) 时间点Data    sx = np.arange(batch_start,batch_start+time_steps*batch_size)           .reshape((batch_size,time_steps))/(10*np.pi)    seq = np.sin(sx)    res = np.cos(sx)    batch_start += time_steps    # return shape==> (batch, step, input)    return [seq[:, :, np.newaxis], res[:, :, np.newaxis], sx]

定义LTSMRNN主体结构

class LSTMRNN(object):    def __init__(self, n_steps, input_size, output_size, cell_size, batch_size):        self.n_steps = n_steps        self.input_size = input_size        self.output_size = output_size        self.cell_size = cell_size        self.batch_size = batch_size        with tf.name_scope('inputs'):            self.xs = tf.placeholder(tf.float32, [None, n_steps, input_size], name='xs')            self.ys = tf.placeholder(tf.float32, [None, n_steps, output_size], name='ys')        with tf.variable_scope('in_hidden'):            self.add_input_layer()        with tf.variable_scope('LSTM_cell'):            self.add_cell()        with tf.variable_scope('out_hidden'):            self.add_output_layer()        with tf.name_scope('cost'):            self.compute_cost()        with tf.name_scope('train'):            self.train_op = tf.train                            .AdamOptimizer(learning_rate)                            .minimize(self.cost)

添加输入层

def add_input_layer(self):    l_in_x = tf.reshape(self.xs, [-1, self.input_size], name='2_2D')  # (batch*n_step, in_size)    # Ws (in_size, cell_size)    Ws_in = self._weight_variable([self.input_size, self.cell_size])    # bs (cell_size, )    bs_in = self._bias_variable([self.cell_size,])    # l_in_y = (batch * n_steps, cell_size)    with tf.name_scope('Wx_plus_b'):        l_in_y = tf.matmul(l_in_x, Ws_in) + bs_in    # reshape l_in_y ==> (batch, n_steps, cell_size)    self.l_in_y = tf.reshape(l_in_y, [-1, self.n_steps, self.cell_size], name='2_3D')

添加RNN的cell

def add_cell(self):    lstm_cell = rnn.BasicLSTMCell(self.cell_size)    with tf.name_scope('initial_state'):        self.cell_init_state = lstm_cell.zero_state(self.batch_size, dtype=tf.float32)    self.cell_outputs, self.cell_final_state = tf.nn.dynamic_rnn(lstm_cell, self.l_in_y, initial_state=self.cell_init_state, time_major=False)

添加输出层

def add_output_layer(self):    # shape ==> (batch * steps, cell_size)    l_out_x = tf.reshape(self.cell_outputs, [-1, self.cell_size], name='2_2D')    Ws_out = self._weight_variable([self.cell_size, self.output_size])    bs_out = self._bias_variable([self.output_size, ])    # shape = (batch * steps, output_size)    with tf.name_scope('Wx_plus_b'):        self.pred = tf.matmul(l_out_x, Ws_out) + bs_out

计算损失和评估模型

def compute_cost(self):    losses = tf.contrib.legacy_seq2seq.sequence_loss_by_example(                    [tf.reshape(self.pred, [-1], name='reshape_pred')],                    [tf.reshape(self.ys, [-1], name='reshape_target')],                    [tf.ones([self.batch_size * self.n_steps], dtype=tf.float32)],                    average_across_timesteps=True,                    softmax_loss_function=self.ms_error,                    name='losses'    )    with tf.name_scope('average_cost'):        self.cost = tf.div( tf.reduce_sum(losses, name='losses_sum'), self.batch_size,name='average_cost')        tf.summary.scalar('cost', self.cost)def ms_error(self, labels, logits):    return tf.square(tf.subtract(labels, logits))

定义权重变量

def _weight_variable(self, shape, name='weights'):    initializer = tf.random_normal_initializer(mean=0., stddev=1.,)    return tf.get_variable(shape=shape, initializer=initializer, name=name)

定义偏置变量

def _bias_variable(self, shape, name='biases'):    initializer = tf.constant_initializer(0.1)    return tf.get_variable(name=name, shape=shape, initializer=initializer)

开始训练测试

if __name__ == '__main__':    model = LSTMRNN(time_steps, input_size, output_size, cell_size, batch_size)    with tf.Session() as sess:        #tensorboard        merged = tf.summary.merge_all()        writer = tf.summary.FileWriter("logs", sess.graph)        sess.run(tf.global_variables_initializer())        plt.ion()        plt.show()        for i in range(training_steps):            seq, res, xs = get_batch()  # 提取 batch data            if i == 0:                # create initial state                feed_dict = {                    model.xs: seq,                    model.ys: res                }            else :                # use last state as the initial state for this run                feed_dict = {                    model.xs: seq,                    model.ys: res,                    model.cell_init_state: state                }            _, cost, state, pred = sess.run( [model.train_op, model.cost, model.cell_final_state, model.pred],feed_dict=feed_dict)            # 画线            plt.plot(xs[0, :], res[0].flatten(), 'r', xs[0, :], pred.flatten()[:time_steps], 'b--')            plt.ylim((-1.2, 1.2))            plt.draw()            plt.pause(0.3)            if i % 20 == 0:                print('cost: ', round(cost, 4))                result = sess.run(merged, feed_dict)                writer.add_summary(result, i)

运输结果：


上面两幅图都是数据上的展示 从波形图看，LSTMRNN的准确度越来越高，基本已经和sin曲线吻合了。计算的偏差也是越来越低，偏差小于0.1。
在tensorboard可以看到神经图，图的结构如下：

图的左边就是这个例子的LSTMRNN的组成结构 有三层的layer组成，两个hidden layer (input/output)+一个cell。
展开这三个layer

hidden layer 包括一个权重和偏执和输入数据，在inputer layer的输入数据先转成二维的数据在输出成3维的数据，在output layer中将cell输出的数据再转成二维数据再经过Wx_plus_b输出结果。
在cell中包括一个rnn的cell和一个initial_state,initial_state在每一次batch循环时被final_state代替。
tf中的bppt如下：