TensorFlow雙向迴圈神經網路

鑑於單向迴圈神經網路某些情況下的不足，提出了雙向迴圈神經網路。因為是需要能關聯未來的資料，而單向迴圈神經網路屬於關聯歷史資料，所以對於未來資料提出反向迴圈神經網路，兩個方向的網路結合到一起就能關聯歷史與未來了。

雙向迴圈神經網路按時刻展開的結構如下，可以看到向前和向後層共同連線著輸出層，其中包含了6個共享權值，分別為輸入到向前層和向後層兩個權值、向前層和向後層各自隱含層到隱含層的權值、向前層和向後層各自隱含層到輸出層的權值。

可以由下列式子表示

實驗內容：使用TensorFlow通過雙向迴圈神經網路演算法對手寫數字進行識別。

原始碼：

from __future__
 
 import print_function
import tensorflow as tf
from tensorflow.contrib import rnn
from tensorflow.examples.tutorials.mnist import input_data
import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"

mnist=input_data.read_data_sets("/home/yxcx/tf_rnn",one_hot=True)

#Traning Parameters
learning_rate=0.001
training_step
 
=10000
batch_size=128
display_step=400

#Network Parmeters
num_input=28
timestep=28
num_hidden=128
num_classes=10

#tf Graph input
X=tf.placeholder("float32",[None,timestep,num_input])
Y=tf.placeholder("float32",[None,num_classes])

#Define weights
weights={
    'out':tf.Variable(tf.random_normal([2*num_hidden,num_classes]))
}
biases
 
={
    'out':tf.Variable(tf.random_normal([num_classes]))
}

def BiRNN(X,weights,biases):
    x=tf.unstack(X,timestep,1)

    #define lstm cells with tensorflow
    #Forward direction cell
    lstm_fw_cell=rnn.BasicLSTMCell(num_hidden,forget_bias=1.0)
    #Backward direction cell
    lstm_bw_cell=rnn.BasicLSTMCell(num_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:
        outputs=rnn.static_bidirectional_rnn(lstm_fw_cell,lstm_bw_cell,x,dtype=tf.float32)

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

logits=BiRNN(X,weights,biases)
prediction=tf.nn.softmax(logits)

#Define loss and optimizer
loss_op=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=Y))
optimizer=tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
train_op=optimizer.minimize(loss_op)

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

#Initialize Variable
init=tf.global_variables_initializer()

#start training
with tf.Session() as sess:
    # Run the initializer
    sess.run(init)

    for step in range(1,training_step+1):
        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,timestep,num_input))
        # Run optimizetion op
        sess.run(train_op,feed_dict={X:batch_x,Y:batch_y})
        if step % display_step == 0 or step==1:
            #Calculate batch loss and accuracy
            loss,acc=sess.run([loss_op,accuracy],feed_dict={X:batch_x,Y:batch_y})
            print("Step "+str(step)+ ",Minbatch Loss="+"{:.4f}".format(loss)+",Training Accuracy="+"{:.3f}".format(acc))
    print("Optimization Finished!")

    #Calculate accuracy for 128 mnist test images
    test_len=128
    test_data=mnist.test.images[:test_len].reshape((-1,timestep,num_input))
    test_label=mnist.test.labels[:test_len]
    print("Test Accuracy:",sess.run(accuracy,feed_dict={X:test_data,Y:test_label}))

結果截圖：