1.dynamic_rnn与static_rnn区别。
static_rnn | dynamic_rnn | ||
不同 | 输入数据格式 | [seq_length,batch_size,embed_size] | [batch,seq_length,embed_size] |
输出数据格式 | [seq_length,batch_size,embed_size] | [batch,seq_length,embed_size] | |
最后时刻输出 | static_rnn_output[-1] | tf.transpose(dynamic_rnn_output, [1, 0, 2])[-1] | |
内部训练方式 | 静态 rnn的意思就是按照样本时间序列个数(n_steps)展开,在图中创建(n_steps)个序列的cell。 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。模型中会带有第个序列中间态的信息,利于调试。 | 动态rnn的意思是只创建样本中的一个序列RNN,其他序列数据会通过循环进入该RNN运算。 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。 | |
相同 | batch_szie | 一个batch_size中的数据长度一致 | 一个batch_size中的数据长度一致 |
2.例子:
static_rnn
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])
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
x1 = tf.unstack(x, n_steps, 1)
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
outputs, states = tf.contrib.rnn.static_rnn(lstm_cell, x1, dtype=tf.float32)
#取最后一条输出信息,(outputs[-1])
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None)
learning_rate = 0.001
training_iters = 100000
display_step = 10
# 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))
# 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 = 128
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}))
dynamic_rnn
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])
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
outputs,_ = tf.nn.dynamic_rnn(lstm_cell,x,dtype=tf.float32)
outputs = tf.transpose(outputs, [1, 0, 2])
#取最后一条输出信息,(outputs[-1])
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None)
learning_rate = 0.001
training_iters = 100000
display_step = 10
# 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))
# 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 = 128
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}))
参考:
https://www.jianshu.com/p/1b1ea45fab47
https://blog.csdn.net/qq1483661204/article/details/78997644