RNN实践一：LSTM实现MNIST数字分类

将MNIST数据集实现手写分类，代码转自周莫烦的Github。
输入为[None, 784] 的image(28*28)数据。
1、将输入数据[None, 784]->[None, 28, 28]; 注：[None, time_step, input_data];
2、线性隐含层：线性变换[None, 28, 28]->[None, 28, 128]；注：128是LSTM的节点数，将每行输入28的数据长度变为128长度。X = X*W_in+Bias_in;
3、设计128个节点数的LSTM，输出为[None, 28, 128]；注：[None, time_step, LSTM_num];
4、线性隐含层：线性变化[None, 28, 128]->[None, 28, 10]；
5、transpose操作：output：[None, 28, 10]->[28, None, 10];
使用output[-1]进行误差计算；注：output[-1]表示最后一个时间节点的输出作为结果输出（读完28行数据后）。

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data# set random seed for comparing the two result calculationstf.set_random_seed(1)# this is datamnist = input_data.read_data_sets('MNIST_data', one_hot=True)# hyperparameterslr = 0.001training_iters = 100000batch_size = 128n_inputs = 28   # MNIST data input (img shape: 28*28)n_steps = 28    # time stepsn_hidden_units = 128   # neurons in hidden layern_classes = 10      # MNIST classes (0-9 digits)# tf Graph inputx = tf.placeholder(tf.float32, [None, n_steps, n_inputs])y = tf.placeholder(tf.float32, [None, n_classes])# Define weightsweights = {    # (28, 128)    'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),    # (128, 10)    'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))}biases = {    # (128, )    'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),    # (10, )    'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))}def RNN(X, weights, biases):    # hidden layer for input to cell    ########################################    # transpose the inputs shape from    # X ==> (128 batch * 28 steps, 28 inputs)    X = tf.reshape(X, [-1, n_inputs])    # into hidden    # 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_steps, n_hidden_units])    # cell    ##########################################    # basic LSTM Cell.    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:        cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)    else:        cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units)    # lstm cell is divided into two parts (c_state, h_state)    init_state = cell.zero_state(batch_size, dtype=tf.float32)    # You have 2 options for following step.    # 1: tf.nn.rnn(cell, inputs);    # 2: tf.nn.dynamic_rnn(cell, inputs).    # If use option 1, you have to modified the shape of X_in, go and check out this:    # https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py    # In here, we go for option 2.    # dynamic_rnn receive Tensor (batch, steps, inputs) or (steps, batch, inputs) as X_in.    # Make sure the time_major is changed accordingly.    outputs, final_state = tf.nn.dynamic_rnn(cell, X_in, initial_state=init_state, time_major=False)    # hidden layer for output as the final results    #############################################    # results = tf.matmul(final_state[1], weights['out']) + biases['out']    # # or    # unpack to list [(batch, outputs)..] * steps    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:        outputs = tf.unpack(tf.transpose(outputs, [1, 0, 2]))    # states is the last outputs    else:        outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))    results = tf.matmul(outputs[-1], weights['out']) + biases['out']    # shape = (128, 10)\    return resultspred = 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))with tf.Session() as sess:    # tf.initialize_all_variables() no long valid from    # 2017-03-02 if using tensorflow >= 0.12    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:        init = tf.initialize_all_variables()    else:        init = tf.global_variables_initializer()    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_steps, 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