tensorflow 实现rnn

本文主要用于讨论官方自带的一个例子，rnn，用于多对一的情况，也就是用于图像分类，
先看下tensorflow的版本，下面在代码低版本可能运行不了：

In [1]: import tensorflow as   tf
In [2]: tf.__version__
Out[2]: '1.1.0-rc0'

代码：

import tensorflow as tf
from  tensorflow.contrib import  rnn
from  tensorflow.examples.tutorials.mnist import input_data
mnist=input_data.read_data_sets("../MNIST_data",one_hot=True)
lr=0.001
training_iters=1000000
batch_size=128
n_inputs=28
n_step=28
n_hidden_unis=128
n_classes=10
x=tf.placeholder(tf.float32,[None,n_step,n_inputs])
y=tf.placeholder(tf.float32,[None,n_classes])
weights={
    'in':tf.Variable(tf.random_normal([n_inputs,n_hidden_unis])),
    'out':tf.Variable(tf.random_normal([n_hidden_unis,n_classes]))
}
biases={
    'in':tf.Variable(tf.constant(0.1,shape=[n_hidden_unis,])),
    'out':tf.Variable(tf.constant(0.1,shape=[n_classes,]))
}
def  RNN(_X,weights,biases):
    _X = tf.transpose(_X, [1, 0, 2])  # permute n_steps and batch_size
    _X = tf.reshape(_X, [-1, n_inputs])  # (n_steps*batch_size, n_input)
    _X = tf.matmul(_X, weights['in']) + biases['in']
    lstm_cell = rnn.BasicLSTMCell(n_hidden_unis, forget_bias=1.0)
    _init_state=lstm_cell.zero_state(batch_size,dtype=tf.float32)
    _X = tf.split(_X, n_step,0 )  # n_steps * (batch_size, n_hidden)
    outputs, states = rnn.static_rnn(lstm_cell, _X, initial_state=_init_state)
    # Get inner loop last output
    return tf.matmul(outputs[-1], weights['out']) + biases['out']
pred=RNN(x,weights,biases)
cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))
train_op=tf.train.AdagradOptimizer(lr).minimize(cost)
correct_pred=tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
accuracy=tf.reduce_mean(tf.cast(correct_pred,tf.float32))
init=tf.global_variables_initializer()
with  tf.Session() as sess:
    sess.run(init)
    step=0
    while step*batch_size<training_iters:
        batch_xs,batch_ys=mnist.train.next_batch(batch_size)
        batch_xs=batch_xs.reshape([batch_size,n_step,n_inputs])
        sess.run(train_op,feed_dict={
            x:batch_xs,
            y:batch_ys
        })
        if  step%20==0:
            print(sess.run(accuracy,feed_dict={
                x: batch_xs,
                y: batch_ys
            }))
        step+=1

结果：

0.921875
0.953125
0.96875
0.953125
0.960938
0.976562
0.96875
0.960938
0.960938
0.945312
0.960938