tensorflow-mnist数据集训练

程序如下；

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_RAGE_BASE = 0.8
LEARNING_RAGE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 3000
MOVING_AVERAGE_DECAY = 0.99

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)

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]))
    
    y = inference(x, None, weights1, biases1, weights2, biases2)
    global_step = tf.Variable(0, trainable=False)
    
    variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_average.apply(tf.trainable_variables())
    average_y = inference(x, variable_average, weights1, biases1, weights2, biases2)
    print(y.get_shape())
    print(y.get_shape())
    lo = tf.argmax(y_, 1)
    print(lo.get_shape())
    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)
    
    #计算L2正则化损失函数
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    regularization = regularizer(weights1)+regularizer(weights2)
    loss = cross_entropy_mean + regularization
    
    learning_rate = tf.train.exponential_decay(LEARNING_RAGE_BASE, global_step,
                                               mnist.train.num_examples/BATCH_SIZE, LEARNING_RAGE_DECAY)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    #在训练神经网络模型时，每过一遍数据既需要通过反向传播来更新神经网络中的参数，又要更新每一个参数的滑动平均值
    #为了一次完成多个操作，Tensorflow提供了tf.control_dependencies和tf.group两种机制，两者等价
    #train_op = tf.group(train_step, variables_averages_op)
    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()
        #准备验证数据，在神经网络训练过程中会通过验证数据来大致判断停止条件和判断训练的效果
        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%200 == 0:
                validate_acc = sess.run(accuracy, feed_dict=validate_feed)
                print("After %d training steps, 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 steps, test accuracy is %g" % (TRAINING_STEPS, test_acc))

def main(argv=None):
    mnist = input_data.read_data_sets("/tmp/data", one_hot=True)
    train(mnist)
    #xs, ys = mnist.train.next_batch(10)
    #print(ys)

if __name__=="__main__":
    tf.app.run()