实现一个双向的RNN（用于分类的）

提示

如果代码中出现了你不懂的接口，请翻看本人博客分类中名为 “tensorflow学习”的类目中，本人肯定一定有的

tf.nn.static_bidirectional_rnn

请看本人这篇博客

实现一个双向的RNN,用于MNIST分类

代码来自这里，本人改了一些

#!/usr/bin/env python
# coding: utf-8

# In[1]:


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)


# Training Parameters
learning_rate = 0.001
training_steps = 10000
batch_size = 128
display_step = 200

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

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

def BiRNN(x):
    # Define lstm cells with tensorflow
    # Forward direction cell
    x=tf.unstack(x,axis=1)
    lstm_fw_cell=tf.nn.rnn_cell.LSTMCell(num_hidden,forget_bias=1.0)
    # Backward direction cell
    lstm_bw_cell =tf.nn.rnn_cell.LSTMCell(num_hidden, forget_bias=1.0)
    try:
        outputs,_ , _=tf.nn.static_bidirectional_rnn(lstm_fw_cell,lstm_bw_cell,x,dtype=tf.float32)
    except Exception:
        outputs=tf.nn.static_bidirectional_rnn(lstm_fw_cell,lstm_bw_cell,x,dtype=tf.float32)
    
    out=tf.layers.dense(outputs[-1],num_classes,use_bias=True)
    return out
  

logits=BiRNN(X)

probas=tf.nn.softmax(logits)

pred_class=tf.argmax(probas,-1)
accuracy=tf.reduce_mean(tf.cast(tf.equal(pred_class,tf.argmax(Y,-1)),tf.float32))

loss_op=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=Y))


optimizer=tf.train.AdamOptimizer(learning_rate=learning_rate)


train_op=optimizer.minimize(loss_op)

init_op=tf.global_variables_initializer()


with tf.Session() as sess:
    sess.run(init_op)
    for step in range(1, training_steps+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, timesteps, num_input))
        # Run optimization op (backprop)
        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) + ", Minibatch 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, timesteps, num_input))
    test_label = mnist.test.labels[:test_len]
    print("Testing Accuracy:",         sess.run(accuracy, feed_dict={X: test_data, Y: test_label}))