TensorFlow 学习笔记 - MNIST 数字识别

本例子很好的定义了一个经典的 TensorFlow 学习示例

读者可以好好体悟其中的流程与经典做法，建议熟练掌握。该网络是一个三层的全连接神经网络，定义了基本的 NN 学习流程。

• mnist_inference.py

import tensorflow as tf

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))
    if regularizer is not None:
        tf.add_to_collection('losses', regularizer(weights))
    return weights


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))
        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

• mnist_train.py

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

os.environ["CUDA_VISIBLE_DEVICES"] = "1"

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "MNIST_model/"
MODEL_NAME = "mnist_model"


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)
    y = mnist_inference.inference(x, regularizer)
    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())
    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'))
    # 使用阶梯衰减 learning rate
    # staircase = True, global_step / decay_steps 会被转化成整数
    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')

    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)


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


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

• mnist_eval.py

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

# 加载的时间间隔。
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}

        # 测试时，不关注正则化损失的值，所以这里用于计算正则化损失的函数被设置为 None。
        # 调用封装好的函数来计算前向传播的结果。
        y = mnist_inference.inference(x, None)
        # 注意，这种方式计算的是 accuracy，不是 machine learning 中的 Precision，注意两者的区别。
        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        # 使用滑动平均模型让模型更加 robust
        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        # variables_to_restore 是为了在保持模型的时候方便使用滑动平均的参数，如果不使用这个保存，那模型就会保存所有参数，除非你提前设定，
        # 就是在保存的时候指定保存变量也是可以的，比如saver = tf.train.Saver([v])这样就可以指定保存变量v，
        # 在模型导入的时候只有这个变量会被导入。
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                # tf.train.get_checkpoint_state() 函数会通过 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:
                    # 此时加载的模型，所有变量都被赋值为其对应的滑动平均变量
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    for v in tf.global_variables():
                        print(v.name, ":", v.eval())
                    print("#####################")
                    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
            # sleep 10 秒
            time.sleep(EVAL_INTERVAL_SECS)


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


if __name__ == '__main__':
    main()