TensorFlow学习笔记(6) TensorFlow最佳实践样例程序

在第三篇中编写了一个程序来解决MNIST问题，这是一个没有持久化训练好的模型。当程序退出时，训练好的模型就再也无法使用了，这导致得到的模型无法被重用。结合变量管理机制及模型持久化机制，对该程序进行进一步的优化重构。

优化重构之后的程序分为三个：第一个是mnist_inference.py，定义前向传播的过程及参数；第二个是mnist_train.py，定义神经网络的训练过程；第三个是mnist_eval.py，定义神经网络的测试过程。

mnist_inference.py

import tensorflow as tf

#定义神经网络结构相关的参数
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

#定义函数创建或者加载变量，并生成正则化损失加入损失集合
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

#定义神经网络的前向传播过程
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(0.1))
        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(0.1))
        layer2 = tf.matmul(layer1, weights) + biases

    return layer2

无论在训练时还是测试时，都可以直接调用inference这个函数，而不用关心具体的神经网络结构。

mnist_train.py

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


# 配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
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 = 30000
MOVING_AVERAGE_DECAY = 0.99 #滑动平均衰减率

#模型保存的路径和文件名
MODEL_SAVE_PATH = '/mnist_model/'
MODEL_SAVE_NAME = 'mnist_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(REGULARIZATION_RATE)

    #直接使用mnist_inference.py中定义的前向传播结果
    y = mnist_inference.inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 生成一个滑动平均的类，并在所有变量上使用滑动平均
    variables_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variables_averages.apply(tf.trainable_variables())

    # 计算交叉熵及当前barch中的所有样例的交叉熵平均值,并求出损失函数
    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'))

    # 定义指数衰减式的学习率以及训练过程
    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)
    train_op = tf.group(train_step, variables_averages_op)  # 打包
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')

    #初始化TF持久化类
    saver = tf.train.Saver()

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())

        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 steps, loss on training batch is %g'% (step, loss_value))
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_SAVE_NAME), global_step=global_step)

def main(argv=None):
    mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
    train(mnist)

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

在训练过程中，每1000轮输出一次在当前训练batch上损失函数的大小来估计训练的效果。并且每1000轮保存一次训练好的模型，这样通过一个单独的测试程序，更加方便地在滑动平均模型上做测试。

mnist_eval.py

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))  # 判断两张量的每一维是否相等，相等返回True，不等返回False
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))  # cast将布尔值转化为float32 求均值即得正确率

        #通过变量重命名的方式来加载模型，这样就不需要调动滑动平均的函数来求平均值
        variables_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variables_averages.variables_to_restore()

        saver = tf.train.Saver(variables_to_restore)

        #每隔10s调用一次计算正确率的过程以检测训练过程中正确率的变化
        while True:
            with tf.Session() as sess:
                #tf.train.get_checkpoint_state通过checkpoint文件自动找到目录中最新模型的文件名
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    #ckpt.model_checkpoint_path：表示模型存储的位置，不需要提供模型的名字，它会去查看checkpoint文件，看看最新的是谁，叫做什么。
                    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 steps, 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("MNIST_data", one_hot=True)
    evaluate(mnist)

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

测试程序每隔10s运行一次，每次运行都是读取最新保存地模型，并验证其正确率。

源自：Tensorflow 实战Google深度学习框架_郑泽宇

TensorFlow学习笔记(6) TensorFlow最佳实践样例程序

猜你喜欢