Tensorflow學習記錄7 RNN+LSTM 分類例子

"""
Based on: Recurrent Neural Network & Long Short-Term Memory

Task: Consider all lines of the photo, and predict the number that it means.
"""

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

# this is data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

# hyperparameters
lr = 0.001
training_iters = 100000  # recurrent times
batch_size = 128

n_inputs = 28  # MNIST data input(img shape:28*28)
n_step = 28  # time steps  (28 lines in the photo)
n_hidden_unis = 128  # neurons in hidden layer
n_classes = 10   # MNIST classes(0-9 digits)

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_step, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

# Define weights
weights = {
    # (28, 128)
    'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_unis])),
    # (128, 10)
    'out': tf.Variable(tf.random_normal([n_hidden_unis, n_classes]))
}
biases = {
    # (128,)
    'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_unis, ])),
    # (10,)
    'out': tf.Variable(tf.constant(1.0, shape=[n_classes, ]))
}


def RNN(X, weights, biases):
    # hidden layer for input to cell
    #######################################################
    # X (128 batch, 28 steps, 28 inputs)
    # ==> (128*28, 28 inputs)
    X = tf.reshape(X, [-1, n_inputs])
    # X_in ==> (128 batch*28 steps, 128 hidden)
    X_in = tf.matmul(X, weights['in'] + biases['in'])
    # X_in ==> (128 batch, 28 steps, 128 hidden)
    X_in = tf.reshape(X_in, [-1, n_step, n_hidden_unis])

    # cell  Long Short-Term Memory
    #######################################################
    lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_unis, forget_bias=1.0, state_is_tuple=True)
    # lstm cell is divided into two parts(c_state, m_state)
    _init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)

    # ouput is a list contains the result of per step
    ouputs, states = tf.nn.dynamic_rnn(lstm_cell, X_in, initial_state=_init_state, time_major=False)

    # hidden layer for output as the final results
    #######################################################
    result = tf.matmul(states[1], weights['out']) + biases['out']

    return result


pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
train_op = tf.train.AdamOptimizer(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

（另外說一下： 調用tensorflow的程序，命令時要小心，如果和tensorflow內置程序名字相同，會報：“has no attribute”錯誤，此時應修改自己程序的名字；還有tf出很久了，更新了很多，一些函數的名字、調用方法有所改動，這時不必慌張，百度就行）

運行結果：