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

import argparse
import sys

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

max_step = 1000 # 最大迭代次数
learning_rate = 0.001  # 学习率
dropout = 0.9  # dropout时随机保留神经元的比例

data_dir = ''  # 样本数据存储的路径
log_dir = ''  # 输出日志保存的路径

mnist = input_data.read_data_sets(data_dir,one_hot=True)

sess = tf.InteractiveSession()

with tf.name_scope('input'):
  x = tf.placeholder(tf.float32, [None, 784], name='x-input')
  y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')

with tf.name_scope('input_reshape'):
  image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
  tf.summary.image('input', image_shaped_input, 10)

def weight_variable(shape):
  """Create a weight variable with appropriate initialization."""
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  """Create a bias variable with appropriate initialization."""
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

def variable_summaries(var):
  """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
  with tf.name_scope('summaries'):
   # 计算参数的均值，并使用tf.summary.scaler记录
   mean = tf.reduce_mean(var)
   tf.summary.scalar('mean', mean)

   # 计算参数的标准差
   with tf.name_scope('stddev'):
    stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
   # 使用tf.summary.scaler记录记录下标准差，最大值，最小值
   tf.summary.scalar('stddev', stddev)
   tf.summary.scalar('max', tf.reduce_max(var))
   tf.summary.scalar('min', tf.reduce_min(var))
   # 用直方图记录参数的分布
   tf.summary.histogram('histogram', var)

def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
  """Reusable code for making a simple neural net layer.
  It does a matrix multiply, bias add, and then uses relu to nonlinearize.
  It also sets up name scoping so that the resultant graph is easy to read,
  and adds a number of summary ops.
  """
  # 设置命名空间
  with tf.name_scope(layer_name):
   # 调用之前的方法初始化权重w，并且调用参数信息的记录方法，记录w的信息
   with tf.name_scope('weights'):
    weights = weight_variable([input_dim, output_dim])
    variable_summaries(weights)
   # 调用之前的方法初始化权重b，并且调用参数信息的记录方法，记录b的信息
   with tf.name_scope('biases'):
    biases = bias_variable([output_dim])
    variable_summaries(biases)
   # 执行wx+b的线性计算，并且用直方图记录下来
   with tf.name_scope('linear_compute'):
    preactivate = tf.matmul(input_tensor, weights) + biases
    tf.summary.histogram('linear', preactivate)
   # 将线性输出经过激励函数，并将输出也用直方图记录下来
   activations = act(preactivate, name='activation')
   tf.summary.histogram('activations', activations)

   # 返回激励层的最终输出
   return activations

hidden1 = nn_layer(x, 784, 500, 'layer1')

with tf.name_scope('dropout'):
  keep_prob = tf.placeholder(tf.float32)
  tf.summary.scalar('dropout_keep_probability', keep_prob)
  dropped = tf.nn.dropout(hidden1, keep_prob)

y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

with tf.name_scope('loss'):
  # 计算交叉熵损失（每个样本都会有一个损失）
  diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
  with tf.name_scope('total'):
   # 计算所有样本交叉熵损失的均值
   cross_entropy = tf.reduce_mean(diff)

tf.summary.scalar('loss', cross_entropy)

with tf.name_scope('train'):
  train_step = tf.train.AdamOptimizer(learning_rate).minimize(
    cross_entropy)

with tf.name_scope('accuracy'):
  with tf.name_scope('correct_prediction'):
   # 分别将预测和真实的标签中取出最大值的索引，弱相同则返回1(true),不同则返回0(false)
   correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  with tf.name_scope('accuracy'):
   # 求均值即为准确率
   accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)

# summaries合并
merged = tf.summary.merge_all()
# 写到指定的磁盘路径中
train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph)
test_writer = tf.summary.FileWriter(log_dir + '/test')

# 运行初始化所有变量
tf.global_variables_initializer().run()

def feed_dict(train):
  """Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
  if train:
   xs, ys = mnist.train.next_batch(100)
   k = dropout
  else:
   xs, ys = mnist.test.images, mnist.test.labels
   k = 1.0
  return {x: xs, y_: ys, keep_prob: k}

for i in range(max_steps):
  if i % 10 == 0: # 记录测试集的summary与accuracy
   summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
   test_writer.add_summary(summary, i)
   print('Accuracy at step %s: %s' % (i, acc))
  else: # 记录训练集的summary
   if i % 100 == 99: # Record execution stats
    run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
    run_metadata = tf.RunMetadata()
    summary, _ = sess.run([merged, train_step],
               feed_dict=feed_dict(True),
               options=run_options,
               run_metadata=run_metadata)
    train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
    train_writer.add_summary(summary, i)
    print('Adding run metadata for', i)
   else: # Record a summary
    summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
    train_writer.add_summary(summary, i)
 train_writer.close()
 test_writer.close()

tensorboard --logdir=

Starting TensorBoard 41 on port 6006
(You can navigate to http://127.0.1.1:6006)