Tensorflow训练神经网络

以下代码摘自《Tensorflow实战Google 深度学习框架》。

由于这段代码包含了激活函数去线性化，多层神经网络，指数衰减学习率，正则化防止过拟合，滑动平均稳定模型等手段，涵盖了神经网络模型的精华，摘录于此。

注：书中的原始数据集可以在 🔗http://yann.lecun.com/exdb/mnist/ 下载

     另外书中代码： cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_, 1))

      应改为： cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))

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  #学习率的衰减率

REGULARIZATION_RATE = 0.0001  #正则化损失函数系数
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99  #滑动平均衰减率


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_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)

    variables_averages_op = variable_averages.apply(tf.trainable_variables())

    averages_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)  #交叉熵均值



    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)  #正则化损失函数
    regularization = regularizer(weights1) + regularizer(weights2)  #计算模型的正则化损失

    loss = cross_entropy_mean + regularization #总损失等于交叉熵损失和正则化损失的和

    #设置实属衰减的学习率，参数分别为：基础学习率，当前迭代的轮数，需要迭代的次数，学习率的衰减速度
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, \
                                               mnist.train.num_examples/BATCH_SIZE, LEARNING_RATE_DECAY)

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

    #train_op = tf.group(train_step, variables_averages_op) #等价于下边两行代码
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')

    correct_prediction = tf.equal(tf.arg_max(averages_y, 1), tf.arg_max(y_, 1))

    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


    # 初始化回话并开始训练过程。
    with tf.Session() as sess:
        #tf.global_variables_initializer().run()
        init_op = tf.global_variables_initializer()
        sess.run(init_op)
        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}
        test_feed = {x: mnist.test.images, y_: mnist.test.labels}

        # 循环的训练神经网络。
        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):
    mnist = input_data.read_data_sets("./path/to/MNIST_data/", one_hot=True)
    train(mnist)

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