tensorflow--静态bilstm

 一.graph结构:

n_input = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 256 # 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])
y = tf.placeholder("float", [None, n_classes])
# Define weights
weights = {
     # Hidden layer weights => 2*n_hidden because of foward + 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):
     x = tf.transpose(x, [1, 0, 2])
     # Reshape to (n_steps*batch_size, n_input)
     x = tf.reshape(x, [-1, n_input])
     # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
     x = tf.split(x, n_steps)
     # Define lstm cells with tensorflow
     # Forward direction cell
     lstm_fw_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
     # Backward direction cell
     lstm_bw_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
     # Get lstm cell output
     try:
		outputs, _, _ = tf.contrib.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.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']

二.官方demo:

import tensorflow as tf
import numpy as np
# Import MINST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
# Parameters
learning_rate = 0.01
max_samples = 400000
batch_size = 128
display_step = 10
# Network Parameters
n_input = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 256 # 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])
y = tf.placeholder("float", [None, n_classes])
# Define weights
weights = {
    # Hidden layer weights => 2*n_hidden because of foward + 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)   
    # Permuting batch_size and n_steps
    x = tf.transpose(x, [1, 0, 2])
    # Reshape to (n_steps*batch_size, n_input)
    x = tf.reshape(x, [-1, n_input])
    # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
    #<tf.Tensor 'split:0' shape=(?, 28) dtype=float32>, <tf.Tensor 'split:1' shape=(?, 28) dtype=float32>...]
    x = tf.split(x, n_steps)
    ##[<tf.Tensor 'unstack:0' shape=(?, 28) dtype=float32>, <tf.Tensor 'unstack:1' shape=(?, 28) dtype=float32>...]
    ## x=tf.unstack(x,n_steps,1)
    
    # Define lstm cells with tensorflow
    # Forward direction cell
    lstm_fw_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
    # Backward direction cell
    lstm_bw_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
    # Get lstm cell output

    outputs, _, _ = tf.contrib.rnn.static_bidirectional_rnn(lstm_fw_cell,
                                                            lstm_bw_cell,
                                                            x,
                                                            dtype=tf.float32)
    return tf.matmul(outputs[-1], weights['out']) + biases['out']

pred = BiRNN(x, weights, biases)
# Define loss and optimizer
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 < max_samples:
        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 = 10000
        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}))