之前在调试6.2.1mnist _eval代码的时候，出现了下面的错误

//下面不阐述本人遇到的错误，直接告诉大家解决办法（以老师给的源代码进行演示）

首先，打开第6章的源代码

 

//点击程序与数据拆分的文件夹， 并将三个文件夹复制到相关路径

 //D:\anaconda\envs\yxy\Lib\site-packages，这是本人的路径，envs\yxy是自己创的那个环境

 

 还需要把MNIST文件夹中的4个压缩包放到如下目录，D:\anaconda\envs\yxy\Lib\site-packages\tensorboard\mnist

 

//之所以放到这个目录是因为

 //当然这里面的路径根据个人情况去改，也可以直接简化为“.\mnist”，系统会自己去寻找。

随后，打开jupyter,先运行mnist_inference代码

import tensorflow.compat.v1 as tf
tf.disable_eager_execution()
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 != 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

再运行mnist_train代码，循环次数可以更改，书上结果是30000次，不过为了节约时间，大家可以改小一点。

import os
import tensorflow.compat.v1 as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
tf.disable_eager_execution()
tf.reset_default_graph()
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000//循环次数
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "./"
MODEL_NAME = "model.ckpt"
def train(mnist):
    print("开始训练！")
    # 定义输入输出placeholder。
    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)
    regularizer = tf.keras.regularizers.l2(REGULARIZATION_RATE)
    # 直接使用mnist_inference.py中定义的前向传播过程
    y = mnist_inference.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)
    variable_averages_op = variable_averages.apply(tf.trainable_variables())
    # 交叉熵与softmax函数一起使用
    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)
    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(name='train')
    saver = tf.train.Saver()
    with tf.Session() as sess:
        print("变量初始化！")
        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})
            # 每1000轮保存一次模型
            #if i+1 % 10 == 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):
    print("进入主函数！")
    mnist = input_data.read_data_sets(r"D:\Anaconda123\Lib\site-packages\tensorboard\mnist", one_hot=True)
    print("准备训练！")
    train(mnist)

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

 

 

最后运行mnist_eval代码

import time
import tensorflow.compat.v1 as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train
tf.disable_eager_execution()
tf.reset_default_graph()
EVAL_INTERVAL_SECS = 10
def evaluate(mnist):
    with tf.Graph().as_default() as g:
        #定义输入与输出的格式
        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}
	       #直接调用封装好的函数来计算前向传播的结果
        y = mnist_inference.inference(x, None)
	 	  #计算正确率
        correcgt_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correcgt_prediction, tf.float32))
	       #通过变量重命名的方式加载模型
        variable_averages = tf.train.ExponentialMovingAverage(0.99)
        variable_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variable_to_restore)
        #每隔10秒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:
                ckpt = tf.train.get_checkpoint_state(r"./")
                if ckpt and ckpt.model_checkpoint_path:
                    #load the model
                    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))
                    return
                else:
                    print('No checkpoint file found')
                    return
            time.sleep(EVAL_INTERVAL_SECS)
def main(argv=None):
    mnist = input_data.read_data_sets(r"D:\Anaconda123\Lib\site-packages\tensorboard\mnist", one_hot=True)
    evaluate(mnist)
if __name__ == '__main__':
    tf.app.run()