基于TensorFlow1.4.0的FNN全连接网络识别MNIST手写数据集

MNIST手写数据集是所有新手入门必经的数据集，数据集比较简单，训练集为50000张手写图片，测试集为张手写图片10000，大小都为28*28，不用自己下载，直接从TensorFlow导入即可

后续随着学习的深入，会继续更新卷积神经网络等，目前全连接网络能实现大概98.3%左右的正确率。欢迎大家一起学习讨论！

以下为源代码，TensorFlow版本为1.4.0

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True)
input_node = 784
output_node = 10
layer1_node_num = 500
batch_size = 100
learning_rate_base = 0.2
learning_rate_decay = 0.999  #学习率衰减率
regularization_rate = 0.0001
train_steps = 30000
moving_average_decay = 0.999

#定义辅助函数
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)

#训练模型的过程
def train(mnist):
    x = tf.placeholder(tf.float32, shape=[None, input_node], name='x-input')
    y = tf.placeholder(tf.float32, shape=[None, output_node], name='y-output')
    #生成隐藏层的参数
    weights1 = tf.Variable(tf.truncated_normal([input_node, layer1_node_num], stddev=0.1, seed=1))
    biases1 = tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[layer1_node_num]))
    weights2 = tf.Variable(tf.truncated_normal([layer1_node_num , output_node], stddev=0.1, seed=1))
    biases2 = tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[output_node]))

    #计算在当前神经网络下前向传播的结果
    y_predict = inference(x, None, weights1, biases1, weights2, biases2)
    global_step = tf.Variable(0, trainable=False)
    variable_average = tf.train.ExponentialMovingAverage(moving_average_decay, global_step)
    variable_average_op = variable_average.apply(tf.trainable_variables())
    average_y = inference(x, variable_average, weights1, biases1, weights2, biases2)
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y, 1), logits=y_predict)
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    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_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)
    with tf.control_dependencies([train_step, variable_average_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(train_steps):
            if i % 1000 == 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 using average model is %g"%(train_steps, test_acc))

def main(argv = None):
    train(mnist)

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