人工智能从入门到精通（13）

tensorflow最佳实践样例程序

当程序退出或者训练好的模型没有保存，都会导致模型无法复用，所以需要每隔一段时间保存一次模型训练的中间结果。
mnist_inference.py

import tensorflow as tf
from tensorflow.python.platform import gfile

INPUT_NODE=784
OUTPUT_NODE=10
LAYER1_NODE=500



def get_weight_variable(shape,regularizer):
    weights =tf.get_variable("weights",shape,initializer=tf.truncated_normal_initializer(stddev=0.1))
    #当给出了正则化生成函数时，将当前变量的正则化损失加入名字为losses的集合。
    #在这里使用了add_to_collection函数将一个张量加入一个集合，而这个集合的名称为losses
    #这是自定义的集合，不在Tensorflow自动管理的集合列表中
    if regularizer!=None:
        tf.add_to_collection('losses',regularizer(weights))
    return weights

#定义神经网络的前向传播过程
def inference(input_tensor,regularizer):
    #声明第一层神经网络的变量并完成前向传播过程
    with tf.variable_scope('layer1'):
        #这里通过tf.get_variable或tf.Variable没有本质区别，
        #因为在训练或是测试中没有在同一个程序中多次调用这个函数，如果在同一个程序中多次调用，在第一次调用之后
        #需要将reuse参数设置为True
        weights=get_weight_variable([INPUT_NODE,LAYER1_NODE], regularizer)
        biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
        layer1=tf.nn.relu(tf.matmul(input_tensor,weights)+biases)
    #类似地声明第二层神经网络的变量并完成前向传播过程
    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

mnist_train.py

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

BATCH_SIZE=100
LEARNING_RATE_BASE=0.8
LEARNING_RATE_DECAY=0.99
REGULAZATION_RATE=0.0001
TRAININIG_STEPS=30000
MOVING_AVERAGE_DECAY=0.99
MODEL_SAVE_PATH="/path/to/model"
MODEL_NAME="model.ckpt"

def train(mnist):
    x=tf.placeholder(tf.float32,[None,mnist_inference.INPUT_NODE],name='x-input')
    y_=tf.placeholder(tf.float32,[None,mnist_inference.OUTPUT_NODE],name='y-input')
    regularizer=tf.contrib.layers.l2_regularizer(REGULAZATION_RATE)
    y=mnist_inference.inference(x,regularizer)
    global_step=tf.Variable(0,trainable=False)
    variable_averages=tf.train.ExponentialMovingAverage(
        MOVING_AVERAGE_DECAY,global_step
    )
    variable_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))
    #书上给出的代码错了，此处必须指定logits和labels，看名字就知道，logits是计算结果，labels是正确答案
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))

#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)

#梯度下降优化损失函数
    train_step=tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    with tf.control_dependencies([train_step, variable_averages_op]):
     train_op=tf.no_op("train")
    saver=tf.train.Saver()
    with tf.Session() as sess:
        tf.initialize_all_variables().run()
        for i in range(TRAININIG_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 taining loss on training batch is %g." % (step,loss_value))
                saver.save(sess,os.path.join(MODEL_SAVE_PATH,MODEL_NAME),global_step=global_step)
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()

输出结果为：

after 1 taining loss on training batch is 3.06166.
after 1001 taining loss on training batch is 0.222248.
after 2001 taining loss on training batch is 0.162017.
after 3001 taining loss on training batch is 0.140595.
after 4001 taining loss on training batch is 0.118097.
after 5001 taining loss on training batch is 0.106785.
after 6001 taining loss on training batch is 0.0992241.

测试

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

import mnist_inference
import mnist_train
EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
        y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
        validate_feed = {x:mnist.validation.images, y_:mnist.validation.labels}

        y = mnist_inference.inference(x, None)

        correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                    accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                    print ("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
                else:
                    print ('NO checkpoint file found')
                    return time.sleep(EVAL_INTERVAL_SECS)


def main(argv=None):
    mnist = input_data.read_data_sets("/path/to/MNIST_data", one_hot=True)
    evaluate(mnist)

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