最近在学习深度学习，之前从图书馆借了本《TensorFlow 实战Google深度学习框架》草草的看了下，最近毕设需要从网上找了个PDF版的仔细啃了起来，发现这本书的代码有些错误，需要做小修改，否则报错运行不起来。可能是因为TensorFlow版本迭代的了原因，之前的一些函数方法都产生了变化。

在第五章，经典的深度学习入门例程：MNIST数字识别问题里，5.2.1里给出的TensorFlow训练神经网络完整例程里：

初始会话里的初始所有变量的代码

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

需要修改为

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

另外在def train(mnist):里的cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_,1))

def train(mnist):
...
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(y, tf.argmax(y_,1))
...

应修改为

cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_, 1), logits=y)

书中将两个参数的位置对调了，导致产生错误

line 1875, in sparse_softmax_cross_entropy_with_logits
    (labels_static_shape.ndims, logits.get_shape().ndims))
ValueError: Rank mismatch: Rank of labels (received 2) should equal rank of logits minus 1 (received 1).

另外还有一些很明显的拼写和排版错误。。。我就不吐槽指出了2333

最后

附上我修改后的完整代码

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import sys
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

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

FLAGS = None


Input_Node = 784
Output_Node = 10

Layer1_Node = 500

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

def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
    if avg_class == None:
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1)+biases1)
        return tf.matmul(layer1, weights2)+biases2
    else:
        layer1 = tf.nn.relu(tf.matmul(input_tensor, avg_class.average(weights1))+avg_class.average(biases1))
        return tf.matmul(layer1, avg_class.average(weights2))+avg_class.average(biases2)

def train(mnist):
    x = tf.placeholder(tf.float32, shape=[None, Input_Node], name='x-input')
    y_ = tf.placeholder(tf.float32, shape=[None, Output_Node], name='y-input')

    weights1 = tf.Variable(tf.truncated_normal([Input_Node, Layer1_Node], stddev=0.1))
    biases1 = tf.Variable(tf.constant(0.1, shape=[Layer1_Node]))

    weights2 = tf.Variable(tf.truncated_normal([Layer1_Node, Output_Node], stddev=0.1))
    biases2 = tf.Variable(tf.constant(0.1, shape=[Output_Node]))

    y = inference(x, None, weights1, biases1, weights2, biases2)

    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())

    average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)

    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_, 1), logits=y)
    #cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)

    regularizer = tf.contrib.layers.l2_regularizer(Regularization_rate)
    regularization = regularizer(weights1)+regularizer(weights2)
    loss = cross_entropy_mean+regularization

    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, variables_averages_op]):
        train_op = tf.no_op(name='train')

        correct_prediction = tf.equal(tf.argmax(average_y, 1), tf.argmax(y_, 1))

        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

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

        validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels}

        test_feed = {x: mnist.test.images, y_: mnist.test.labels}
        for i in range(Training_steps):
            if i % 1000 == 0:
                validate_acc = sess.run(accuracy, feed_dict=validate_feed)
                print("After %d training step(s), validation accuracy "
                      "using average model is %g" % (i, validate_acc))

                xs, ys = mnist.train.next_batch(Batch_size)
                sess.run(train_op, feed_dict={x: xs, y_: ys})
        test_acc = sess.run(accuracy, feed_dict=test_feed)
        print("After %d training step(s), test accuracy using average"
                  "model is %g" % (Training_steps, test_acc))

'''
def main(_):
    mnist = input_data.read_data_sets("/data", one_hot=True)
    train(mnist)

if __name__ == '__main__':
  parser = argparse.ArgumentParser()
  parser.add_argument(
      '--data_dir',
      type=str,
      default='/tmp/tensorflow/mnist/input_data',
      help='Directory for storing input data')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
'''

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

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

另外，因为我的电脑没有独立的GPU，只能使用CPU进行计算，添加代码

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

可以避免出现如下的警告

2018-03-23 22:43:44.983594: I C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\35\tensorflow\core\platform\cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2

这并不是最完美的解决方法，只是眼不见为净的解决方法而已。