TensorFlow实现mnist数字识别

数据集可以从http://yann.lecun.com/exdb/mnist/下载

 

输入为784，中间层有500个节点，输出为10维的向量，激活函数为softmax，loss选用cross_entropy，使用了L2正则化。

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
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 10000
MOVING_AVERAGE_DECAY = 0.99


# 使用variable_scope管理变量
def inference(input_tensor, reuse=False):
    with tf.variable_scope("layer1", reuse=reuse):
        weights = tf.get_variable("weights", [INPUT_NODE, LAYER1_NODE],
                                  initializer=tf.truncated_normal_initializer(stddev=0.1))
        biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.1))
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)

    with tf.variable_scope("layer2", reuse=reuse):
        weights = tf.get_variable("weights", [LAYER1_NODE, OUTPUT_NODE],
                                  initializer=tf.truncated_normal_initializer(stddev=0.1))
        biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.1))
        # layer2 = tf.nn.softmax(tf.matmul(layer1, weights) + biases)
        layer2 = tf.matmul(layer1, weights) + biases
    return layer2


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")

    y = inference(x)

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

    # 计算损失函数
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=y, labels=y_)#tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    # 注意这一段，weights1和weights2都在inference中创建，但是L2正则化需要用到这个变量。
    # 使用variable_scope就能很方便的获取到这两个变量：
    with tf.variable_scope("", reuse=True):
        weights1 = tf.get_variable("layer1/weights")
        weights2 = tf.get_variable("layer2/weights")

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

    correct_prediction = tf.equal(tf.argmax(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 + 1) % 1000 == 0:
                validate_acc = sess.run(accuracy, feed_dict=validate_feed)
                print("After %d training steps, validation accuracy using average model is %f" % (i + 1, 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, validation accuracy using average model is %f" % (TRAINING_STEPS, test_acc))


def main(argv=None):
    mnist = input_data.read_data_sets(r'.\mnist', one_hot=True)
    train(mnist)


if __name__ == "__main__":
    main()

训练结果如下： 

After 1000 training steps, validation accuracy using average model is 0.974400
After 2000 training steps, validation accuracy using average model is 0.979200
After 3000 training steps, validation accuracy using average model is 0.978800
After 4000 training steps, validation accuracy using average model is 0.982200
After 5000 training steps, validation accuracy using average model is 0.983600
After 6000 training steps, validation accuracy using average model is 0.983000
After 7000 training steps, validation accuracy using average model is 0.985000
After 8000 training steps, validation accuracy using average model is 0.983800
After 9000 training steps, validation accuracy using average model is 0.984200
After 10000 training steps, validation accuracy using average model is 0.986000
After 10000 training steps, validation accuracy using average model is 0.980600