BiLSTM官方示例（Tensorflow版）

'''
A Bidirectional Recurrent Neural Network (LSTM) implementation example using TensorFlow library.
This example is using the MNIST database of handwritten digits (http://yann.lecun.com/exdb/mnist/)
Long Short Term Memory paper: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf

Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''

from __future__ import print_function

import tensorflow as tf
from tensorflow.contrib import rnn
import numpy as np

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

'''
To classify images using a bidirectional recurrent 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

# 可以理解为，训练时总共用的样本数
training_iters = 100000

# 每次训练的样本大小
batch_size = 128

# 这个是用来显示的。
display_step = 10

# Network Parameters
# n_steps*n_input其实就是那张图 把每一行拆到每个time step上。
n_input = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # timesteps

# 隐藏层大小
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST total classes (0-9 digits)

# tf Graph input
# [None, n_steps, n_input]这个None表示这一维不确定大小
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])

# Define weights
weights = {
    # Hidden layer weights => 2*n_hidden because of forward + backward cells
    'out': tf.Variable(tf.random_normal([2*n_hidden, n_classes]))
}
biases = {
    'out': tf.Variable(tf.random_normal([n_classes]))
}


def BiRNN(x, weights, biases):

    # Prepare data shape to match `bidirectional_rnn` function requirements
    # Current data input shape: (batch_size, n_steps, n_input)
    # Required shape: 'n_steps' tensors list of shape (batch_size, n_input)

    # Unstack to get a list of 'n_steps' tensors of shape (batch_size, n_input)
    # 变成了n_steps*(batch_size, n_input)
    x = tf.unstack(x, n_steps, 1)

    # Define lstm cells with tensorflow
    # Forward direction cell
    lstm_fw_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
    # Backward direction cell
    lstm_bw_cell = rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)

    # Get lstm cell output
    try:
        outputs, _, _ = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
                                              dtype=tf.float32)
    except Exception: # Old TensorFlow version only returns outputs not states
        outputs = rnn.static_bidirectional_rnn(lstm_fw_cell, lstm_bw_cell, x,
                                        dtype=tf.float32)

    # Linear activation, using rnn inner loop last output
    return tf.matmul(outputs[-1], weights['out']) + biases['out']

pred = BiRNN(x, weights, biases)

# Define loss and optimizer
# softmax_cross_entropy_with_logits：Measures the probability error in discrete classification tasks in which the classes are mutually exclusive
# return a 1-D Tensor of length batch_size of the same type as logits with the softmax cross entropy loss.
# reduce_mean就是对所有数值（这里没有指定哪一维）求均值。
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# 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.global_variables_initializer()

# 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_x, batch_y = mnist.train.next_batch(batch_size)
        # Reshape data to get 28 seq of 28 elements
        batch_x = batch_x.reshape((batch_size, n_steps, n_input))
        # Run optimization op (backprop)
        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
        if step % display_step == 0:
            # Calculate batch accuracy
            acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
            # Calculate batch loss
            loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
            print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
                  "{:.6f}".format(loss) + ", Training Accuracy= " + \
                  "{:.5f}".format(acc))
        step += 1
    print("Optimization Finished!")

    # Calculate accuracy for 128 mnist test images
    test_len = 128
    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}))