时间:2022-12-15 10:32:08 | 栏目:Python代码 | 点击:次
在过去的时间里我们学习了RNN循环神经网络,其结构示意图是这样的:
其存在的最大问题是,当w1、w2、w3这些值小于0时,如果一句话够长,那么其在神经网络进行反向传播与前向传播时,存在梯度消失的问题。
0.925=0.07,如果一句话有20到30个字,那么第一个字的隐含层输出传递到最后,将会变为原来的0.07倍,相比于最后一个字的影响,大大降低。
其具体情况是这样的:
长短时记忆网络就是为了解决梯度消失的问题出现的。
原始RNN的隐藏层只有一个状态h,从头传递到尾,它对于短期的输入非常敏感。
如果我们再增加一个状态c,让它来保存长期的状态,问题就可以解决了。
对于RNN和LSTM而言,其两个step单元的对比如下。
我们把LSTM的结构按照时间维度展开:
我们可以看出,在n时刻,LSTM的输入有三个:
1、当前时刻网络的输入值;
2、上一时刻LSTM的输出值;
3、上一时刻的单元状态。
LSTM的输出有两个:
1、当前时刻LSTM输出值;
2、当前时刻的单元状态。
3、LSTM独特的门结构
LSTM用两个门来控制单元状态cn的内容:
1、遗忘门(forget gate),它决定了上一时刻的单元状态cn-1有多少保留到当前时刻;
2、输入门(input gate),它决定了当前时刻网络的输入c’n有多少保存到单元状态。
LSTM用一个门来控制当前输出值hn的内容:
输出门(output gate),它决定了当前时刻单元状态cn有多少输出。
tf.contrib.rnn.BasicLSTMCell( num_units, forget_bias=1.0, state_is_tuple=True, activation=None, reuse=None, name=None, dtype=None )
在使用时,可以定义为:
lstm_cell = tf.contrib.rnn.BasicLSTMCell(self.cell_size, forget_bias=1.0, state_is_tuple=True)
在定义完成后,可以进行状态初始化:
self.cell_init_state = lstm_cell.zero_state(self.batch_size, dtype=tf.float32)
tf.nn.dynamic_rnn( cell, inputs, sequence_length=None, initial_state=None, dtype=None, parallel_iterations=None, swap_memory=False, time_major=False, scope=None )
在LSTM的最后,需要用该函数得出结果。
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)
返回的是一个元组 (outputs, state):
outputs
:LSTM的最后一层的输出,是一个tensor。如果为time_major== False,则它的shape为[batch_size,max_time,cell.output_size]。如果为time_major== True,则它的shape为[max_time,batch_size,cell.output_size]。
states
:states是一个tensor。state是最终的状态,也就是序列中最后一个cell输出的状态。一般情况下states的形状为 [batch_size, cell.output_size],但当输入的cell为BasicLSTMCell时,states的形状为[2,batch_size, cell.output_size ],其中2也对应着LSTM中的cell state和hidden state。
整个LSTM的定义过程为:
def add_input_layer(self,): #X最开始的形状为(256 batch,28 steps,28 inputs) #转化为(256 batch*28 steps,128 hidden) l_in_x = tf.reshape(self.xs, [-1, self.input_size], name='to_2D') #获取Ws和Bs Ws_in = self._weight_variable([self.input_size, self.cell_size]) bs_in = self._bias_variable([self.cell_size]) #转化为(256 batch*28 steps,256 hidden) with tf.name_scope('Wx_plus_b'): l_in_y = tf.matmul(l_in_x, Ws_in) + bs_in # (batch * n_steps, cell_size) ==> (batch, n_steps, cell_size) # (256*28,256)->(256,28,256) self.l_in_y = tf.reshape(l_in_y, [-1, self.n_steps, self.cell_size], name='to_3D') def add_cell(self): #神经元个数 lstm_cell = tf.contrib.rnn.BasicLSTMCell(self.cell_size, forget_bias=1.0, state_is_tuple=True) #每一次传入的batch的大小 with tf.name_scope('initial_state'): self.cell_init_state = lstm_cell.zero_state(self.batch_size, dtype=tf.float32) #不是主列 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) def add_output_layer(self): #设置Ws,Bs Ws_out = self._weight_variable([self.cell_size, self.output_size]) bs_out = self._bias_variable([self.output_size]) # shape = (batch,output_size) # (256,10) with tf.name_scope('Wx_plus_b'): self.pred = tf.matmul(self.cell_final_state[-1], Ws_out) + bs_out
该例子为手写体识别例子,将手写体的28行分别作为每一个step的输入,输入维度均为28列。
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import numpy as np mnist = input_data.read_data_sets("MNIST_data",one_hot = "true") BATCH_SIZE = 256 # 每一个batch的数据数量 TIME_STEPS = 28 # 图像共28行,分为28个step进行传输 INPUT_SIZE = 28 # 图像共28列 OUTPUT_SIZE = 10 # 共10个输出 CELL_SIZE = 256 # RNN 的 hidden unit size,隐含层神经元的个数 LR = 1e-3 # learning rate,学习率 def get_batch(): #获取训练的batch batch_xs,batch_ys = mnist.train.next_batch(BATCH_SIZE) batch_xs = batch_xs.reshape([BATCH_SIZE,TIME_STEPS,INPUT_SIZE]) return [batch_xs,batch_ys] class LSTMRNN(object): #构建LSTM的类 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 #输入输出 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, output_size], name='ys') #直接加层 with tf.variable_scope('in_hidden'): self.add_input_layer() #增加LSTM的cell with tf.variable_scope('LSTM_cell'): self.add_cell() #直接加层 with tf.variable_scope('out_hidden'): self.add_output_layer() #计算损失值 with tf.name_scope('cost'): self.compute_cost() #训练 with tf.name_scope('train'): self.train_op = tf.train.AdamOptimizer(LR).minimize(self.cost) #正确率计算 self.correct_pre = tf.equal(tf.argmax(self.ys,1),tf.argmax(self.pred,1)) self.accuracy = tf.reduce_mean(tf.cast(self.correct_pre,tf.float32)) def add_input_layer(self,): #X最开始的形状为(256 batch,28 steps,28 inputs) #转化为(256 batch*28 steps,128 hidden) l_in_x = tf.reshape(self.xs, [-1, self.input_size], name='to_2D') #获取Ws和Bs Ws_in = self._weight_variable([self.input_size, self.cell_size]) bs_in = self._bias_variable([self.cell_size]) #转化为(256 batch*28 steps,256 hidden) with tf.name_scope('Wx_plus_b'): l_in_y = tf.matmul(l_in_x, Ws_in) + bs_in # (batch * n_steps, cell_size) ==> (batch, n_steps, cell_size) # (256*28,256)->(256,28,256) self.l_in_y = tf.reshape(l_in_y, [-1, self.n_steps, self.cell_size], name='to_3D') def add_cell(self): #神经元个数 lstm_cell = tf.contrib.rnn.BasicLSTMCell(self.cell_size, forget_bias=1.0, state_is_tuple=True) #每一次传入的batch的大小 with tf.name_scope('initial_state'): self.cell_init_state = lstm_cell.zero_state(self.batch_size, dtype=tf.float32) #不是主列 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) def add_output_layer(self): #设置Ws,Bs Ws_out = self._weight_variable([self.cell_size, self.output_size]) bs_out = self._bias_variable([self.output_size]) # shape = (batch,output_size) # (256,10) with tf.name_scope('Wx_plus_b'): self.pred = tf.matmul(self.cell_final_state[-1], Ws_out) + bs_out def compute_cost(self): self.cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits = self.pred,labels = self.ys) ) def _weight_variable(self, shape, name='weights'): initializer = np.random.normal(0.0,1.0 ,size=shape) return tf.Variable(initializer, name=name,dtype = tf.float32) def _bias_variable(self, shape, name='biases'): initializer = np.ones(shape=shape)*0.1 return tf.Variable(initializer, name=name,dtype = tf.float32) if __name__ == '__main__': #搭建 LSTMRNN 模型 model = LSTMRNN(TIME_STEPS, INPUT_SIZE, OUTPUT_SIZE, CELL_SIZE, BATCH_SIZE) sess = tf.Session() sess.run(tf.global_variables_initializer()) #训练10000次 for i in range(10000): xs, ys = get_batch() #提取 batch data if i == 0: #初始化data feed_dict = { model.xs: xs, model.ys: ys, } else: feed_dict = { model.xs: xs, model.ys: ys, model.cell_init_state: state #保持 state 的连续性 } #训练 _, cost, state, pred = sess.run( [model.train_op, model.cost, model.cell_final_state, model.pred], feed_dict=feed_dict) #打印精确度结果 if i % 20 == 0: print(sess.run(model.accuracy,feed_dict = { model.xs: xs, model.ys: ys, model.cell_init_state: state #保持 state 的连续性 }))