Tensorflow学习（四）——递归神经网络RNN

实现一个简单的RNN（代码如下）

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


mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
batch_size = 50
num_batch = mnist.train.num_examples // batch_size
# 输入（图片尺寸28*28）
num_input = 28      # 一行28个数据
max_time = 28       # 行数量
LSTM_size = 100     # 隐藏单元数量（block数量）
num_classes = 10    # 10个分类（对应输出）

x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
weights = tf.Variable(tf.truncated_normal([LSTM_size, num_classes], stddev=0.1))
biases = tf.Variable(tf.constant(0.1, shape=[num_classes]))


def RNN(X):
    # inputs格式固定:[batch_size, max_time, num_input]
    inputs = tf.reshape(X, [-1, max_time, num_input])
    # 定义LSTM基本的cell
    LSTM_cell = rnn.BasicLSTMCell(LSTM_size)
    outputs, final_state = tf.nn.dynamic_rnn(LSTM_cell, inputs, dtype=tf.float32)
    results = tf.nn.softmax(tf.matmul(final_state[1], weights) + biases)
    return results


prediction = RNN(x)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=prediction, labels=y))
train = tf.train.AdamOptimizer(0.0001).minimize(loss)
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(6):
        for batch in range(num_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train, feed_dict={x: batch_xs, y: batch_ys})
        acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
        print('iter' + str(epoch) + ', testing accuracy:' + str(acc))