使用静态堆叠和动态堆叠
通过静态生成的RNN网络，生成过程所需的时间会更长，网络所占有的内存会更多，导出的模型会更大，模型中会带有第个序列中间态的信息，利于调试。在使用时必须与训练的样本序列个数相同。通过动态生成的RNN网络，所占用内存较少。模型中只会有最后的状态，在使用时还能支持不同的序列个数。
怎么堆叠rnn
把多个rnn部件添加到lsit中，通过tf.contrib.rnn.MultiRNNCell函数可以把rnn按顺序链接，堆叠rnn就是多个rnn进行堆叠,每个lstm的单元个数可以不一样。
gru = tf.contrib.rnn.GRUCell(n_hidden*2)
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden)
mcell = tf.contrib.rnn.MultiRNNCell([lstm_cell,gru])
堆叠静态rnn
stacked_rnn = []
for i in range(3):
stacked_rnn.append(tf.contrib.rnn.LSTMCell(n_hidden))
mcell = tf.contrib.rnn.MultiRNNCell(stacked_rnn)
x1 = tf.unstack(x, n_steps, 1)
outputs, states = tf.contrib.rnn.static_rnn(mcell, x1, dtype=tf.float32)
堆叠动态rnn
stacked_rnn = []
for i in range(3):
stacked_rnn.append(tf.contrib.rnn.LSTMCell(n_hidden))
mcell = tf.contrib.rnn.MultiRNNCell(stacked_rnn)
outputs,states = tf.nn.dynamic_rnn(mcell,x,dtype=tf.float32)#(?, 28, 256)
outputs = tf.transpose(outputs, [1, 0, 2])
比较以下代码：
堆叠动态RNN：
# -*- coding: utf-8 -*-
import tensorflow as tf
# 导入 MINST 数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("c:/user/administrator/data/", one_hot=True)
n_input = 28 # MNIST data 输入 (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST 列别 (0-9 ，一共10类)
batch_size = 128
tf.reset_default_graph()
# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])
gru = tf.contrib.rnn.GRUCell(n_hidden*2)
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden)
mcell = tf.contrib.rnn.MultiRNNCell([lstm_cell,gru])
x1 = tf.unstack(x, n_steps, 1)
outputs, states = tf.contrib.rnn.static_rnn(mcell, x1, dtype=tf.float32)
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None)
learning_rate = 0.001
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
training_iters = 100000
display_step = 10
# 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
if step % display_step == 0:
# 计算批次数据的准确率
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print (" Finished!")
# 计算准确率 for 128 mnist test images
test_len = 100
test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input))
test_label = mnist.test.labels[:test_len]
print ("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
堆叠静态RNN：
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("c:/user/administrator/data/", one_hot=True)
n_input = 28 # MNIST data 输入 (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST 列别 (0-9 ，一共10类)
batch_size = 128
tf.reset_default_graph()
# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])
gru = tf.contrib.rnn.GRUCell(n_hidden*2)
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden)
mcell = tf.contrib.rnn.MultiRNNCell([lstm_cell,gru])
outputs,states = tf.nn.dynamic_rnn(mcell,x,dtype=tf.float32)#(?, 28, 256)
outputs = tf.transpose(outputs, [1, 0, 2])#(28, ?, 256) 28个时序，取最后一个时序outputs[-1]=(?,256)
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None)
learning_rate = 0.001
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
training_iters = 100000
display_step = 10
# 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
if step % display_step == 0:
# 计算批次数据的准确率
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print (" Finished!")
# 计算准确率 for 128 mnist test images
test_len = 100
test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input))
test_label = mnist.test.labels[:test_len]
print ("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: test_data, y: test_label}))