python - 如何在 TensorFlow 中使用批量标准化？

Question

我想在 TensorFlow 中使用 批量标准化。我在 core/ops/nn_ops.cc 中找到了相关的 C++ 源代码.但是，我没有在 tensorflow.org 上找到它。

BN 在 MLP 和 CNN 中有不同的语义，所以我不确定这个 BN 到底是做什么的。

我也没有找到名为 MovingMoments 的方法。

Answer 1

2016 年 7 月更新 在 TensorFlow 中使用批量标准化的最简单方法是通过 contrib/layers 中提供的高级接口(interface)。 , tflearn , 或 slim .

如果你想 DIY，上一个答案: 自发布以来，文档字符串已得到改进 - 请参阅 docs comment in the master branch而不是你找到的那个。它特别说明了它是 tf.nn.moments 的输出。

您可以在 batch_norm test code 中看到一个非常简单的使用示例。 .对于更真实的使用示例，我在帮助器类下方包含了我为自己使用而草草写下的使用说明(不提供任何保证!):

"""A helper class for managing batch normalization state.                   

This class is designed to simplify adding batch normalization               
(http://arxiv.org/pdf/1502.03167v3.pdf) to your model by                    
managing the state variables associated with it.                            

Important use note:  The function get_assigner() returns                    
an op that must be executed to save the updated state.                      
A suggested way to do this is to make execution of the                      
model optimizer force it, e.g., by:                                         

  update_assignments = tf.group(bn1.get_assigner(),                         
                                bn2.get_assigner())                         
  with tf.control_dependencies([optimizer]):                                
    optimizer = tf.group(update_assignments)                                

"""

import tensorflow as tf


class ConvolutionalBatchNormalizer(object):
  """Helper class that groups the normalization logic and variables.        

  Use:                                                                      
      ewma = tf.train.ExponentialMovingAverage(decay=0.99)                  
      bn = ConvolutionalBatchNormalizer(depth, 0.001, ewma, True)           
      update_assignments = bn.get_assigner()                                
      x = bn.normalize(y, train=training?)                                  
      (the output x will be batch-normalized).                              
  """

  def __init__(self, depth, epsilon, ewma_trainer, scale_after_norm):
    self.mean = tf.Variable(tf.constant(0.0, shape=[depth]),
                            trainable=False)
    self.variance = tf.Variable(tf.constant(1.0, shape=[depth]),
                                trainable=False)
    self.beta = tf.Variable(tf.constant(0.0, shape=[depth]))
    self.gamma = tf.Variable(tf.constant(1.0, shape=[depth]))
    self.ewma_trainer = ewma_trainer
    self.epsilon = epsilon
    self.scale_after_norm = scale_after_norm

  def get_assigner(self):
    """Returns an EWMA apply op that must be invoked after optimization."""
    return self.ewma_trainer.apply([self.mean, self.variance])

  def normalize(self, x, train=True):
    """Returns a batch-normalized version of x."""
    if train:
      mean, variance = tf.nn.moments(x, [0, 1, 2])
      assign_mean = self.mean.assign(mean)
      assign_variance = self.variance.assign(variance)
      with tf.control_dependencies([assign_mean, assign_variance]):
        return tf.nn.batch_norm_with_global_normalization(
            x, mean, variance, self.beta, self.gamma,
            self.epsilon, self.scale_after_norm)
    else:
      mean = self.ewma_trainer.average(self.mean)
      variance = self.ewma_trainer.average(self.variance)
      local_beta = tf.identity(self.beta)
      local_gamma = tf.identity(self.gamma)
      return tf.nn.batch_norm_with_global_normalization(
          x, mean, variance, local_beta, local_gamma,
          self.epsilon, self.scale_after_norm)

请注意，我将其称为 ConvolutionalBatchNormalizer，因为它使用 tf.nn.moments 对轴 0、1 和 2 求和，而对于非卷积使用你可能只需要轴 0。

如果您使用它，我们将不胜感激。