Tensorflow实例：mnist最佳实践

Tensorflow最佳实践mnist程序

在Tensorflow实例：mnist中已经给出了一个完整的Tensorflow程序来解决MNIST问题。然而这个程序的可扩展性并不好。存在的问题如下：

1. 计算前向传播的函数需要将所有变量都传入，当神经网络的结果变得更加复杂、参数更多时，程序可读性会变得非常差。大量冗余代码，降低编程的效率。变量管理给出了解决方法。

2. 当程序退出时，训练好的模型也就无法被使用了，这导致模型无法被重用。

3. 在训练的过程中需要每隔一段时间保存一次模型训练的中间结果。

最佳实践

1. 将训练和测试分成两个独立的程序，这可以使得每一个组件更加灵活。比如训练神经网络的程序可以持续输出训练好的模型，而测试程序可以每隔一段时间检验最新模型的正确率。
2. 将前向传播的过程抽象成一个单独的库函数。因为神经网络的前向传播过程在训练和测试的过程中都会用到，所以通过库函数的方式使用起来更加方便，而且保证训练和测试过程中使用的前向传播方法一定是一致的。

代码

重构之后的代码将会被拆成3个程序，
1. mnist_inference.py：定义了前向传播的过程已经神经网络中的参数。
2. mnist_train.py：定义了神经网络的训练过程
3. mnist_eval.py：定义了测试过程

mnist_inference.py

# _*_ coding: utf-8 _*_import tensorflow as tf# 定义神经网络结构相关的参数INPUT_NODE = 784OUTPUT_NODE = 10LAYER1_NODE = 500# 通过tf.get_variable函数来获取变量。在训练神经网络时会创建这些变量；在测试时会通过保存的模型加载这些变量的取值。# 而且更加方便的是，因为可以在变量加载时将滑动平均变量重命名，所以可以直接通过同样的名字在训练时使用变量自身。而在测试时# 使用变量的滑动平均值。在这个函数中也会将变量的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):    # 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"):        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)    # 类似的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

# _*_ coding: utf-8 _*_import osimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data# 加载mnist_inference.py中定义的常量和前向传播的函数import mnist_inference# 配置神经网络的参数BATCH_SIZE = 100LEARNING_RATE_BASE = 0.8LEARNING_RATE_DECAY = 0.99REGULARAZTION_RATE = 0.0001TRAIN_STEPS = 30000MOVING_AVERAGE_DECAY = 0.99MODEL_SAVE_PATH = "./model/"MODEL_NAME = "model2.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(REGULARAZTION_RATE)    y = mnist_inference.inference(x, regularizer)    global_step = tf.Variable(0, trainable=False)    variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)    variable_average_op = variable_average.apply(        tf.trainable_variables())    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_, 1), logits=y)    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=global_step, decay_steps=mnist.train.num_examples / BATCH_SIZE,                                               decay_rate=LEARNING_RATE_DECAY)    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)    with tf.control_dependencies([train_step, variable_average_op]):        train_op = tf.no_op(name='train')    saver = tf.train.Saver()    with tf.Session() as sess:        tf.global_variables_initializer().run()        for i in range(TRAIN_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_NAME), global_step=global_step)def main(argv=None):    mnist = input_data.read_data_sets("E:\科研\TensorFlow教程\MNIST_data", one_hot=True)    train(mnist)if __name__ == '__main__':    tf.app.run()

mnist_eval.py

# _*_ coding: utf-8 _*_import timeimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport mnist_inferenceimport mnist_trainEVAL_INTERVAL_SECS = 10def 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(x, regularizer=None)        correct_prediction = tf.equal(tf.argmax(y, 1), tf.matmul(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)                    if __name__ == '__main__':                        global_step = ckpt.model_checkpoint_path\                            .split('/')[-1].split('-')[-1]                        accuracy_score = sess.run(accuracy,                                                  feed_dict=validate_feed)                        print("After %d 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("E:\科研\TensorFlow教程\MNIST_data", one_hot=True)    evaluate(mnist)if __name__ == '__main__':    tf.app.run()