TensorBoard 的使用

作者: Yigit_dev | 来源:发表于2017-12-23 16:41 被阅读0次

本篇博客主要介绍下 tensorboard 的使用方法，tensorboard 是 tensorflow 中一个可视化训练过程中数据的工具，它不需要单独安装，tensorflow 安装过程中已经将其装好了，它可以通过tensorflow程序运行过程中产生的日志文件可视化tensorflow程序的运行状态，它和tensorflow程序跑在不同的进程。下面基于官方的例子源码来讲解 mnist_with_summaries.py

编码阶段

1.添加关心的tensor或者Variable变量到tensorboard中

tf.summary.image 添加需要观察的图片信息

  with tf.name_scope('input_reshape'):#使用命名空间，将一些节点信息统一在一起，使计算图看起来整洁
    image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
    tf.summary.image('input', image_shaped_input, 10) # 参数：name、tensor、max_outputs
    #max_outputs默认是3，我们这里让其多显示几张就写成了10
    #使用命名空间后，image的名字类似：input_reshape/input/xxxxx

tf.summary.scalar 添加需要观察的变量信息

  # 定义一个对Variable变量（这里有weight和bias）的命名空间公共方法，并计算他们的mean、stddev
  # max、min、histogram等值并收集在Tensorboard中供用户查看
  def variable_summaries(var):
    """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
    with tf.name_scope('summaries'):
      mean = tf.reduce_mean(var)
      tf.summary.scalar('mean', mean) #参数 ：name, values
      with tf.name_scope('stddev'):
        stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
      tf.summary.scalar('stddev', stddev)
      tf.summary.scalar('max', tf.reduce_max(var)) #名字类似：xxx/summaries/max
      tf.summary.scalar('min', tf.reduce_min(var))
      tf.summary.histogram('histogram', var)

tf.summary.histogram 添加对变量或者tensor取值范围的直方图信息

      with tf.name_scope('Wx_plus_b'):
        preactivate = tf.matmul(input_tensor, weights) + biases
        tf.summary.histogram('pre_activations', preactivate) #参数 ：name, values

2.汇总所有操作节点，并通过FileWriter创建保存运行过程中信息的文件

tf.summary.merge_all 汇总所有节点操作，并定义两个文件记录器FileWriter

  #汇总所有操作，并定义两个文件记录器FileWriter
  merged = tf.summary.merge_all()
  train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph) #添加整个计算图
  test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')

3.训练或者测试过程中运行汇总的节点merged，会产生运行信息并将这些信息写入上一步中创建的文件当中

train_writer.add_summary 往文件中写入信息

        #记录训练时运算时间和内存占用情况
        run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE) #设置trace_level
        run_metadata = tf.RunMetadata() #定义tensorflow运行元信息
        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)#添加训练元信息
        train_writer.add_summary(summary, i)

完整的代码如下：

# coding=UTF-8
import argparse
import os
import sys

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

FLAGS = None


def train():
  # Import data
  mnist = input_data.read_data_sets(FLAGS.data_dir,
                                    fake_data=FLAGS.fake_data)

  # 默认的session，可以先构建session后定义操作，如果使用tf.Session()需要在启动session之前构建整个计算图，
  # 然后启动该计算图。它还可以直接在不声明session的条件下直接使用run()，eval()
  sess = tf.InteractiveSession()


  # Create a multilayer model.

  # Input placeholders
  with tf.name_scope('input'): #使用命名空间，将一些节点信息统一在一起，使计算图看起来整洁
    x = tf.placeholder(tf.float32, [None, 784], name='x-input')
    y_ = tf.placeholder(tf.int64, [None], 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) #使用命名空间后，image的名字类似：input_reshape/input/xxxxx

  # We can't initialize these variables to 0 - the network will get stuck.
  #模型参数初始化
  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)

  # 定义一个对Variable变量（这里有weight和bias）的命名空间公共方法，并计算他们的mean、stddev
  # max、min、histogram等值并收集在Tensorboard中供用户查看
  def variable_summaries(var):
    """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
    with tf.name_scope('summaries'):
      mean = tf.reduce_mean(var)
      tf.summary.scalar('mean', mean)
      with tf.name_scope('stddev'):
        stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
      tf.summary.scalar('stddev', stddev)
      tf.summary.scalar('max', tf.reduce_max(var)) #名字类似：xxx/summaries/max
      tf.summary.scalar('min', tf.reduce_min(var))
      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.
    """
    # 定义一个MLP多层神经网络来训练数据，包括：初始化weight和bias、做一个矩阵相乘再加上一个偏置项，然后经过一个非线性
    #激活函数
    # Adding a name scope ensures logical grouping of the layers in the graph.
    with tf.name_scope(layer_name):
      # This Variable will hold the state of the weights for the layer
      with tf.name_scope('weights'):
        weights = weight_variable([input_dim, output_dim])
        variable_summaries(weights)
      with tf.name_scope('biases'):
        biases = bias_variable([output_dim])
        variable_summaries(biases)
      with tf.name_scope('Wx_plus_b'):
        preactivate = tf.matmul(input_tensor, weights) + biases
        tf.summary.histogram('pre_activations', preactivate)
      activations = act(preactivate, name='activation')
      tf.summary.histogram('activations', activations)
      return activations

  hidden1 = nn_layer(x, 784, 500, 'layer1') #使用前面定义的网络

  #使用dropout
  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)

  # Do not apply softmax activation yet, see below.
  # 这里激活函数用的是全等映射，即直接将输入复制给输出
  y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

  with tf.name_scope('cross_entropy'):
    # The raw formulation of cross-entropy,
    # tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.softmax(y)), reduction_indices=[1]))
    # can be numerically unstable.
    # So here we use tf.losses.sparse_softmax_cross_entropy on the
    # raw logit outputs of the nn_layer above, and then average across
    # the batch.
    with tf.name_scope('total'):
      #计算softmax和交叉熵
      cross_entropy = tf.losses.sparse_softmax_cross_entropy(
          labels=y_, logits=y)
  tf.summary.scalar('cross_entropy', cross_entropy)

  #使用Adam优化器对损失进行优化
  with tf.name_scope('train'):
    train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
        cross_entropy)

  #统计正确率
  with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
      correct_prediction = tf.equal(tf.argmax(y, 1), y_)
    with tf.name_scope('accuracy'):
      accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  tf.summary.scalar('accuracy', accuracy)

  # Merge all the summaries and write them out to
  # ./logs/(by default)
  #汇总所有操作，并定义两个文件记录器FileWriter
  merged = tf.summary.merge_all()
  train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
  test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
  tf.global_variables_initializer().run()

  # Train the model, and also write summaries.
  # Every 10th step, measure test-set accuracy, and write test summaries
  # All other steps, run train_step on training data, & add training summaries
  #定义一个feed_dict函数来确定要训练数据还是测试数据
  def feed_dict(train):
    """Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
    if train or FLAGS.fake_data:
      xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
      k = FLAGS.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(FLAGS.max_steps):
    if i % 10 == 0:  # Record summaries and test-set 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:  # Record train set summaries, and train
      if i % 100 == 99:  # Record execution stats
        #记录训练时运算时间和内存占用情况
        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)#添加训练元信息
        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() #记得关闭
  test_writer.close()


def main(_):
  if tf.gfile.Exists(FLAGS.log_dir):#文件存在就删除，重新训练生成
    tf.gfile.DeleteRecursively(FLAGS.log_dir)
  tf.gfile.MakeDirs(FLAGS.log_dir)
  train()


if __name__ == '__main__':
  parser = argparse.ArgumentParser() #命令行参数解析，没有默认值就提示用户输入
  parser.add_argument('--fake_data', nargs='?', const=True, type=bool,
                      default=False,
                      help='If true, uses fake data for unit testing.')
  parser.add_argument('--max_steps', type=int, default=1000,
                      help='Number of steps to run trainer.')
  parser.add_argument('--learning_rate', type=float, default=0.001,
                      help='Initial learning rate')
  parser.add_argument('--dropout', type=float, default=0.9,
                      help='Keep probability for training dropout.')
  parser.add_argument(
      '--data_dir',
      type=str,
      default="./mnist_data",
      help='Directory for storing input data')
  parser.add_argument(
      '--log_dir',
      type=str,
      default="./logs",
      help='Summaries log directory')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

TensorBoard 可视化文件生成

上面代码运行完成后会在train_writer和test_writer指定目录下生成类似"events.out.tfevents.1513910245.N22411D1"这种的文件，然后通过命令行输入命令

tensorboard --logdir=path/to/log-directory #注意这里只需要指定到生成文件的上一级目录就可以了

会有如下提示：

F:\>tensorboard --logdir=./log
TensorBoard 0.4.0rc3 at http://N22411D1:6006 (Press CTRL+C to quit)

最后我们通过将" http://N22411D1:6006"输入谷歌或者火狐浏览器就可以了。

TensorBoard 可视化文件分析

请放大查看原图，图中有注释说明。

SCALARS

统计一些准确率、损失函数、weight等单个值的变化趋势

tensorboard_summary_scalars.PNG

IMAGES

显示你指定的一些图片信息

tensorboard_image.PNG

GRAPHS

显示你定义的整个计算图，包括计算图里面每个节点的详细信息，比如输入输出的shape是多少，内存占用，计算时间占用，节点名称等等

tensorflow_graphs.PNG

DISTRIBUTIONS

显示你指定的一些模型参数随着迭代次数增加的变化趋势

tensorboard_distributions.PNG

HISTOGRAMS