全连接层训练MNIST图片识别——tensorflow

tf1.0

 

主函数中run会调用main

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# mnist数据集相关的常数
INPUT_NODE = 784  # 输入节点，等于图片的像素
OUTPUT_NODE = 10  # 输出节点

# 配置神经网络的参数
LAYER1_NODE = 500  # 隐藏层节点数
BATCH_SIZE = 100  # 一个训练batch中的训练数据个数

LEARNING_RATE_BASE = 0.8  # 基础的学习率
LEARNING_RATE_DECAY = 0.99  # 学习率的衰减率
REGULARIZATION_RATE = 0.0001  # 描述模型复杂度的正则化项在损失函数中的系数
TRAINING_STEPS = 3000  # 训练轮数
MOVING_AVERAGE_DECAY = 0.99  # 滑动平均衰减率


# 设计一个辅助函数，给定神经网络的输入和所有参数，计算神经网络的前向传播结果
# 使用tf.nn.relu激活函数实现去线性化
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
    # 不使用滑动平均类
    if avg_class == None:
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
        return tf.matmul(layer1, weights2) + biases2

    else:
        # 使用滑动平均类
        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
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')
    # 生成隐藏层的参数。
    weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))
    # 生成输出层的参数。
    weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
    biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))

    # 计算不含滑动平均类的前向传播结果
    y = inference(x, None, weights1, biases1, weights2, biases2)

    # 定义训练轮数及相关的滑动平均类
    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)

    # 计算交叉熵及其平均值
    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)

    # 损失函数的计算
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    regularization = regularizer(weights1) + regularizer(weights2)
    loss = cross_entropy_mean + regularization

    # 设置指数衰减的学习率。
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE,
        LEARNING_RATE_DECAY,
        staircase=True)

    # 优化损失函数,loss损失作为梯度下降算法的输入，minimize方法将loss一步步减小
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    # 训练数据时，每过一遍数都需要通过反向传播更新神经网络中的参数和更新每一个参数的滑动平均值
    # tensoflow提供了tf.control_dependencies和tf.group机制来完成操作
    # 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')

    # 计算正确率
    correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    # 初始化会话，并开始训练过程。
    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}

        # 循环的训练神经网络。
        for i in range(TRAINING_STEPS):
            if i % 100 == 0:
                validate_acc, learn_loss = sess.run([accuracy, loss], feed_dict=validate_feed)
                print("After %d training step(s), validation accuracy using average model is %g " % (i, validate_acc))
                print("After %d training step(s), learn loss  is %g                             " % (i, learn_loss))
                # print(sess.run(weights1))

            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):
    # 声明处理MNIST数据集的类，这个类在初始化时会自动下载数据，"MNIST_data"文件夹存放mnist数据集
    mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
    train(mnist)


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

 

 

参考

https://blog.csdn.net/wifimale/article/details/89021980