专栏首页机器学习算法与Python学习TensorFlow:TensorBoard可视化

TensorFlow:TensorBoard可视化

关键字全网搜索最新排名

【机器学习算法】:排名第一

【机器学习】:排名第二

【Python】:排名第三

【算法】:排名第四

我们会再接再厉

成为全网优质的技术类公众号

在学习深度网络框架的过程中,我们发现一个问题,就是如何输出各层网络参数,用于更好地理解,调试和优化网络?针对这个问题,TensorFlow开发了一个特别有用的可视化工具包:TensorBoard,既可以显示网络结构,又可以显示训练和测试过程中各层参数的变化情况。

TensorBoard的输入是tensorflow保存summary data的日志文件。日志文件名的形式如:events.out.tfevents.1467809796.lei-All-Series 或 events.out.tfevents.1467809800.lei-All-Series。TensorBoard可读的summary data有scalar,images,audio,histogram和graph。

代码测试

"""A simple MNIST classifier which displays summaries in TensorBoard.This is an unimpressive MNIST model, but it is a good example of using tf.name_scope to make a graph legible in the TensorBoard graph explorer, and of naming summary tags so that they are grouped meaningfully in TensorBoard. It demonstrates the functionality of every TensorBoard dashboard.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_boolean('fake_data', False, 'If true, uses fake data '
                     'for unit testing.')
flags.DEFINE_integer('max_steps', 1000, 'Number of steps to run trainer.')
flags.DEFINE_float('learning_rate', 0.001, 'Initial learning rate.')
flags.DEFINE_float('dropout', 0.9, 'Keep probability for training dropout.')
flags.DEFINE_string('data_dir', '/tmp/data', 'Directory for storing data')
flags.DEFINE_string('summaries_dir', '/tmp/mnist_logs', 'Summaries directory')
def train():
  # Import data
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True,
                                    fake_data=FLAGS.fake_data)
  sess = tf.InteractiveSession()
  # Create a multilayer model.
  # Input placehoolders
  with tf.name_scope('input'):
    x = tf.placeholder(tf.float32, [None, 784], name='x-input')
    image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
    tf.image_summary('input', image_shaped_input, 10)
    y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
    keep_prob = tf.placeholder(tf.float32)
    tf.scalar_summary('dropout_keep_probability', keep_prob)
  # We can't initialize these variables to 0 - the network will get stuck.
  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, name):
    """Attach a lot of summaries to a Tensor."""
    with tf.name_scope('summaries'):
      mean = tf.reduce_mean(var)
      tf.scalar_summary('mean/' + name, mean)
      with tf.name_scope('stddev'):
        stddev = tf.sqrt(tf.reduce_sum(tf.square(var - mean)))
      tf.scalar_summary('sttdev/' + name, stddev)
      tf.scalar_summary('max/' + name, tf.reduce_max(var))
      tf.scalar_summary('min/' + name, tf.reduce_min(var))
      tf.histogram_summary(name, 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.
    """
    # 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, layer_name + '/weights')
      with tf.name_scope('biases'):
        biases = bias_variable([output_dim])
        variable_summaries(biases, layer_name + '/biases')
      with tf.name_scope('Wx_plus_b'):
        preactivate = tf.matmul(input_tensor, weights) + biases
        tf.histogram_summary(layer_name + '/pre_activations', preactivate)
      activations = act(preactivate, 'activation')
      tf.histogram_summary(layer_name + '/activations', activations)
      return activations
  hidden1 = nn_layer(x, 784, 500, 'layer1')
  dropped = tf.nn.dropout(hidden1, keep_prob)
  y = nn_layer(dropped, 500, 10, 'layer2', act=tf.nn.softmax)
  with tf.name_scope('cross_entropy'):
    diff = y_ * tf.log(y)
    with tf.name_scope('total'):
      cross_entropy = -tf.reduce_mean(diff)
    tf.scalar_summary('cross entropy', cross_entropy)
  with tf.name_scope('train'):
    train_step = tf.train.AdamOptimizer(
        FLAGS.learning_rate).minimize(cross_entropy)
  with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
      correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    with tf.name_scope('accuracy'):
      accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    tf.scalar_summary('accuracy', accuracy)
  # Merge all the summaries and write them out to /tmp/mnist_logs (by default)
  merged = tf.merge_all_summaries()
  train_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/train', sess.graph)
  test_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/test')
  tf.initialize_all_variables().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
  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 summarieis, and train
      summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
      train_writer.add_summary(summary, i)
def main(_):
  if tf.gfile.Exists(FLAGS.summaries_dir):
    tf.gfile.DeleteRecursively(FLAGS.summaries_dir)
  tf.gfile.MakeDirs(FLAGS.summaries_dir)
  train()
if __name__ == '__main__':
  tf.app.run()

运行上述代码之后调用TensorBoard可视化运行结果,

tensorboard --logdir=/tmp/mnist_logs/train/

打开链接 http://0.0.0.0:6006

EVENTS是训练参数统计显示,可以看到整个训练过程中,各个参数的变换情况

GRAPH网络结构显示

HISTOGRAM训练过程参数分布情况显示

本文分享自微信公众号 - 机器学习算法与Python学习(guodongwei1991),作者:昱良

原文出处及转载信息见文内详细说明,如有侵权,请联系 yunjia_community@tencent.com 删除。

原始发表时间:2017-04-27

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • TensorFlow实战:CNN构建MNIST识别(Python完整源码)

    在文章(TensorFlow实战:SoftMax手写体MNIST识别(Python完整源码))中,我们MNIST手写体识别数据集,使用TensorFlow构建了...

    昱良
  • 一个牛逼的 Python 调试工具

    一般情况下,在编写 Python 代码时,如果想弄清楚为什么 Python 代码没有按照预期执行的原因,比如你想知道哪些是正在运行,哪些没有运行,以及局部变量的...

    昱良
  • TensorFlow的安装与初步了解

    今天终于有时间一探滕三福了,TensorFlow(腾三福)是谷歌基于DistBelief进行研发的第二代人工智能学习系统,其命名来源于本身的运行原理。Tenso...

    昱良
  • 中阶API示范

    TensorFlow有5个不同的层次结构:即硬件层,内核层,低阶API,中阶API,高阶API。本章我们将以线性回归为例,直观对比展示在低阶API,中阶API,...

    lyhue1991
  • 低阶API示范

    TensorFlow有5个不同的层次结构:即硬件层,内核层,低阶API,中阶API,高阶API。本章我们将以线性回归为例,直观对比展示在低阶API,中阶API,...

    lyhue1991
  • python实现最大似然函数与结果展示

    AI之禅
  • 深度学习入门实战(三):图片分类中的逻辑回归

    上一讲我们介绍了一下线性回归如何通过TensorFlow训练,这一讲我们介绍下逻辑回归模型,一句话说概括,逻辑回归就是多分类问题。

    serena
  • 机器学习的大局:用神经网络和TensorFlow分类文本

    开发人员常说,如果你想开始机器学习,你应该先学习算法是如何工作的。但是我的经验表明并不是这样子。

    人工智能资讯小编
  • tensorflow学习笔记(三十五):control flow

    tf.cond(pred, fn1, fn2, name=None) 等价于: res = fn1() if pred else fn2() 注意:pred不能...

    ke1th
  • TensorFlow2.X学习笔记(1)--TensorFlow核心概念

    TensorFlow™ 是一个采用 数据流图(data flow graphs),用于数值计算的开源软件库。节点(Nodes)在图中表示数学操作,图中的线(e...

    MiChong

扫码关注云+社区

领取腾讯云代金券