Question

代码如下，使用python 3，Anaconda Spyder3.6，Tensorflow 1.0.0

"""
Created on Sat Oct 14 11:00:54 2017

@author: Han.H
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

INPUT_NODE = 784     
OUTPUT_NODE = 10    
LAYER1_NODE = 500 
BATCH_SIZE = 100      

LEARNING_RATE_BASE = 0.8      
LEARNING_RATE_DECAY = 0.99    
REGULARAZTION_RATE = 0.0001   #lambda
TRAINING_STEPS = 20000        
MOVING_AVERAGE_DECAY = 0.99  

# when not use ExponentialMovingAverage,just nomal fp
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):

    if avg_class == None:

        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
        return tf.matmul(layer1, weights2) + biases2

    else:

        layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1)) + avg_class.average(biases1))
        return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)  

# build a 3-layer full connected NN    
def train(mnist):
    x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
    y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')

    weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))

    weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
    biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))

    # normal fp 
    y = inference(x, None, weights1, biases1, weights2, biases2)

    global_step = tf.Variable(0, trainable=False)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)


    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    # L2
    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
    regularaztion = regularizer(weights1) + regularizer(weights2)
    loss = cross_entropy_mean + regularaztion

    # Set learning rate  
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE,
        LEARNING_RATE_DECAY,
        staircase=True)

    # Gradient descent
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')


    correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
        test_feed = {x: mnist.test.images, y_: mnist.test.labels} 

        for i in range(TRAINING_STEPS):
            if i % 1000 == 0:
                validate_acc = sess.run(accuracy, feed_dict=validate_feed)
                print("After %d training step(s), validation accuracy using average model is %g " % (i, validate_acc))

            xs,ys=mnist.train.next_batch(BATCH_SIZE)
            sess.run(train_op,feed_dict={x:xs,y_:ys})

        test_acc=sess.run(accuracy,feed_dict=test_feed)
        print(("After %d training step(s), test accuracy using average model is %g" %(TRAINING_STEPS, test_acc)))

def main(argv=None):
# Main programme here
    mnist = input_data.read_data_sets("F:/python/MNIST_data/", one_hot=True)
    train(mnist)

if __name__=='__main__':
    main()

此代码没有问题，运行良好。我只是想知道为什么不能使用average_y作为logits来计算交叉熵。我试图这样做。结果很糟糕。准确性随机初始化为0.009.

TensorFlow：为什么使用fp结果y而不是ExponentialMovingAverage fp结果average_y作为cross_entropy的参数？

0 个答案: