TensorFlow人工智能引擎入门教程之九 RNN/LSTM循环神经网络长短期记忆网络使用

[size_batches, seq_length, rnn_size]

_X = tf.transpose(_X, [1, 0, 2])

import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

import tensorflow as tf
from tensorflow.models.rnn import rnn, rnn_cell
import numpy as np

'''
To classify images using a reccurent neural network, we consider every image row as a sequence of pixels.
Because MNIST image shape is 28*28px, we will then handle 28 sequences of 28 steps for every sample.
'''

# Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 128
display_step = 10

# Network Parameters
n_input = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST total classes (0-9 digits)

# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
# Tensorflow LSTM cell requires 2x n_hidden length (state & cell)
istate = tf.placeholder("float", [None, 2*n_hidden])
y = tf.placeholder("float", [None, n_classes])

# Define weights
weights = {
'hidden': tf.Variable(tf.random_normal([n_input, n_hidden])), # Hidden layer weights
'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
'hidden': tf.Variable(tf.random_normal([n_hidden])),
'out': tf.Variable(tf.random_normal([n_classes]))
}

def RNN(_X, _istate, _weights, _biases):

_X = tf.transpose(_X, [1, 0, 2])  # permute n_steps and batch_size

_X = tf.reshape(_X, [-1, n_input]) # (n_steps*batch_size, n_input)

_X = tf.matmul(_X, _weights['hidden']) + _biases['hidden']

lstm_cell = rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0)

_X = tf.split(0, n_steps, _X) # n_steps * (batch_size, n_hidden)

outputs, states = rnn.rnn(lstm_cell, _X, initial_state=_istate)

# Get inner loop last output
return tf.matmul(outputs[-1], _weights['out']) + _biases['out']

pred = RNN(x, istate, weights, biases)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) # Softmax loss
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # Adam Optimizer

# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.initialize_all_variables()

# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_xs = batch_xs.reshape((batch_size, n_steps, n_input))
# Fit training using batch data
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys,
istate: np.zeros((batch_size, 2*n_hidden))})
if step % display_step == 0:
# Calculate batch accuracy
acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys,
istate: np.zeros((batch_size, 2*n_hidden))})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys,
istate: np.zeros((batch_size, 2*n_hidden))})
print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + \
", Training Accuracy= " + "{:.5f}".format(acc)
step += 1
print "Optimization Finished!"
# Calculate accuracy for 256 mnist test images
test_len = 256
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,
istate: np.zeros((test_len, 2*n_hidden))})