Tensorflow学习之mnist数据集实践

机器学习 2017-09-02

    mnist手写数据集是验证算法和框架常用的数据集,下面使用tensorflow进行测试。

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

#参数设定
BATCH_SIZE = 100 
LEARNING_RATE_BASE = 0.8 #基础学习率
LEARNING_RATE_DECAY = 0.99 #衰减率
REGULARIZATION_RATE = 0.0001 #正则化项在损失函数中的系数
TRAINING_STEPS = 30000 #训练轮数
MOVING_AVERAGE_DECAY = 0.99  #滑动平均衰减系数
MODEL_SAVE_PATH = "MNIST_model/"
MODEL_NAME = "mnist_model"

INPUT_NODE = 784  #输入层相当于图片像素
OUTPUT_NODE = 10  #输出层相当于图片类别
LAYER1_NODE = 500 #隐藏节点数

#获取变量
def get_weight_variable(shape, regularizer):
    weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
    if regularizer != None: tf.add_to_collection('losses', regularizer(weights))
    return weights

#前向传播
def inference(input_tensor, regularizer):
    with tf.variable_scope('layer1'):

        weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
        biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
        #计算隐藏层的前向传播结果,使用RELU激活函数
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)

    with tf.variable_scope('layer2'):
        weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
        biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
        layer2 = tf.matmul(layer1, weights) + biases

    return layer2

def train(mnist):
    # 定义输入输出placeholder。
    x = tf.placeholder(tf.float32, [None,INPUT_NODE], name='x-input')
    y_ = tf.placeholder(tf.float32, [None,OUTPUT_NODE], name='y-input')

    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 定义损失函数、学习率、滑动平均操作以及训练过程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    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)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
    learning_rate = tf.train.exponential_decay(
        LEARNING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,
        staircase=True)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')

    # 初始化TensorFlow持久化类。
    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()

        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
            if i % 1000 == 0:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)

 #主程序入口
def main(argv=None):
    mnist = input_data.read_data_sets("C:/Users/Administrator/Desktop/test/datasets/MNIST_data", one_hot=True) #数据集放在指定位置
    train(mnist)

if __name__ == '__main__':
    main()

  使用cpu耗时361.7s后损失率降为0.0364781,表明该数据集识别率很高。


本文由 Tony 创作,采用 知识共享署名 3.0,可自由转载、引用,但需署名作者且注明文章出处。

如果对您有用,您的支持将鼓励我继续创作!