tensorflow训练RNN网络

落日映苍穹つ 2023-07-11 15:21 18阅读 0赞

小彩笔的摸爬滚打之路orz

### 一、本程序的使用环境 ###

python:3.7.4  
tensorflow:1.9.0  
写这个的目的是，请大家在程序开发的过程中千万注意使用的tensorflow版本问题，因为可能出现很多奇奇怪怪的问题  
编写是参考了很多，这位博主的博客：  
[https://www.jianshu.com/p/dfb7cf19f7b9][https_www.jianshu.com_p_dfb7cf19f7b9]

### 二、程序代码 ###

import tensorflow as tf
    import input_data
    from tensorflow.contrib import rnn
    print ("Packages imported")
    
    mnist = input_data.read_data_sets("data/", one_hot=True)
    trainimgs, trainlabels, testimgs, testlabels \
     = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels 
    ntrain, ntest, dim, nclasses \
     = trainimgs.shape[0], testimgs.shape[0], trainimgs.shape[1], trainlabels.shape[1]
    print ("MNIST loaded")
    print('ntrain:',ntrain)
    print('ntest:',ntest)
    print('dim:',dim)
    print('nclasses:',nclasses)

diminput  = 28
    dimhidden = 128
    dimoutput = nclasses
    nsteps    = 28
    W={ 'h1':tf.Variable(tf.random_normal([diminput,dimhidden])),
       'h2':tf.Variable(tf.random_normal([dimhidden, dimoutput]))}
    b={ 'b1':tf.Variable(tf.random_normal([dimhidden])),
       'b2':tf.Variable(tf.random_normal([dimoutput]))}

def _RNN(_X, _W, _b, _nsteps):
        # 1. Permute input from [batchsize, nsteps, diminput] 
        # => [nsteps, batchsize, diminput]
        _X = tf.transpose(_X, [1, 0, 2])
        # 2. Reshape input to [nsteps*batchsize, diminput] 
        _X = tf.reshape(_X, [-1, diminput])
        # 3. Input layer => Hidden layer
        _H = tf.matmul(_X, _W['h1']) + _b['b1']
        # 4. Splite data to 'nsteps' chunks. An i-th chunck indicates i-th batch data 
        _Hsplit = tf.split(_H, _nsteps, 0) 
        # 5. Get LSTM's final output (_LSTM_O) and state (_LSTM_S)
        # Both _LSTM_O and _LSTM_S consist of 'batchsize' elements
        # Only _LSTM_O will be used to predict the output. 
        lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(dimhidden, forget_bias=1.0)
        _LSTM_O, _LSTM_S = rnn.static_rnn(lstm_cell, _Hsplit,dtype=tf.float32)
        # 6. Output
        _O = tf.matmul(_LSTM_O[-1], _W['h2']) + _b['b2']    
        # Return! 
        return { 
            'X': _X, 'H': _H, 'Hsplit': _Hsplit,
            'LSTM_O': _LSTM_O, 'LSTM_S': _LSTM_S, 'O': _O 
        }
    print ("Network ready")

learning_rate = 0.001
    x      = tf.placeholder("float", [None, nsteps, diminput])
    y      = tf.placeholder("float", [None, dimoutput])
    myrnn  = _RNN(x, W, b, nsteps)
    pred   = myrnn['O']
    cost   = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y)) 
    optm   = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) # Adam Optimizer
    accr   = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(pred,1), tf.argmax(y,1)), tf.float32))
    init   = tf.global_variables_initializer()
    print ("Network Ready!")

training_epochs = 5
    batch_size      = 16
    display_step    = 1
    sess = tf.Session()
    sess.run(init)
    print ("Start optimization")
    for epoch in range(training_epochs):
        avg_cost = 0.
        #total_batch = int(mnist.train.num_examples/batch_size)
        total_batch = 100
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            batch_xs = batch_xs.reshape((batch_size, nsteps, diminput))
            # Fit training using batch data
            feeds = { x: batch_xs, y: batch_ys}
            sess.run(optm, feed_dict=feeds)
            # Compute average loss
            avg_cost += sess.run(cost, feed_dict=feeds)/total_batch
        # Display logs per epoch step
        if epoch % display_step == 0: 
            print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
            feeds = { x: batch_xs, y: batch_ys}
            train_acc = sess.run(accr, feed_dict=feeds)
            print (" Training accuracy: %.3f" % (train_acc))
            testimgs = testimgs.reshape((ntest, nsteps, diminput))
            feeds = { x: testimgs, y: testlabels}
            test_acc = sess.run(accr, feed_dict=feeds)
            print (" Test accuracy: %.3f" % (test_acc))
    print ("Optimization Finished.")

运行结果：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]

[https_www.jianshu.com_p_dfb7cf19f7b9]: https://www.jianshu.com/p/dfb7cf19f7b9
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200306144404433.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70