pointnet batch_norm_for_conv2d

outputs = batch_norm_for_conv2d(outputs, is_training, bn_decay=bn_decay, scope='bn')

def batch_norm_for_conv2d(inputs, is_training, bn_decay, scope):
  """ Batch normalization on 2D convolutional maps.
  
  Args:
      inputs:      Tensor, 4D BHWC input maps
      is_training: boolean tf.Varialbe, true indicates training phase
      bn_decay:    float or float tensor variable, controling moving average weight
      scope:       string, variable scope
  Return:
      normed:      batch-normalized maps
  """
  return batch_norm_template(inputs, is_training, scope, [0,1,2], bn_decay)

 batch_norm_for_conv2d根据作者解释，是batch为单位在2d卷积层面进行归一化，具体实现在batch_norm_template中，如下：

def batch_norm_template(inputs, is_training, scope, moments_dims, bn_decay):
  """ Batch normalization on convolutional maps and beyond...
  Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-tensorflow
  
  Args:
      inputs:        Tensor, k-D input ... x C could be BC or BHWC or BDHWC
      is_training:   boolean tf.Varialbe, true indicates training phase
      scope:         string, variable scope
      moments_dims:  a list of ints, indicating dimensions for moments calculation
      bn_decay:      float or float tensor variable, controling moving average weight
  Return:
      normed:        batch-normalized maps
  """
  with tf.variable_scope(scope) as sc:
    num_channels = inputs.get_shape()[-1].value
    beta = tf.Variable(tf.constant(0.0, shape=[num_channels]),
                       name='beta', trainable=True)
    gamma = tf.Variable(tf.constant(1.0, shape=[num_channels]),
                        name='gamma', trainable=True)
    batch_mean, batch_var = tf.nn.moments(inputs, moments_dims, name='moments')
    decay = bn_decay if bn_decay is not None else 0.9
    ema = tf.train.ExponentialMovingAverage(decay=decay)
    # Operator that maintains moving averages of variables.
    ema_apply_op = tf.cond(is_training,
                           lambda: ema.apply([batch_mean, batch_var]),
                           lambda: tf.no_op())
    
    # Update moving average and return current batch's avg and var.
    def mean_var_with_update():
      with tf.control_dependencies([ema_apply_op]):
        return tf.identity(batch_mean), tf.identity(batch_var)
    
    # ema.average returns the Variable holding the average of var.
    mean, var = tf.cond(is_training,
                        mean_var_with_update,
                        lambda: (ema.average(batch_mean), ema.average(batch_var)))
    normed = tf.nn.batch_normalization(inputs, mean, var, beta, gamma, 1e-3)
  return normed

 在pointnet工程中，经过"transformnet1"中的'tconv1'之后产生的output[32,1024,1,64]作为输入，则

num_channels=64

beta = tf.Variable(tf.constant(0.0, shape=[num_channels]),
                       name='beta', trainable=True)
    gamma = tf.Variable(tf.constant(1.0, shape=[num_channels]),
                        name='gamma', trainable=True)

初始化tensor，'beta'，'gamma'，设置在train的时候实时观察，shape为64，类型为float，gama默认为1

momentdims为[0,1,2]是个vector里面的值是0，1，2

batch_mean, batch_var = tf.nn.moments(inputs, moments_dims, name='moments')声明一个batch对应的平均值以及方差tensor（batchsize明明是32为什么平均值及方差是64的tensor，能解释的就是每个batch有64channel，每个channel一个平均值以及方差）

decay = bn_decay沿用的依然是最初声明的指数增加的那个learning rate

ema = tf.train.ExponentialMovingAverage(decay=decay)创建参数的移动平均object

ema_apply_op = tf.cond(is_training,
                       lambda: ema.apply([batch_mean, batch_var]),
                       lambda: tf.no_op())

利用ema保持batch_mean, batch_var的移动平均

normed = tf.nn.batch_normalization(inputs, mean, var, beta, gamma, 1e-3)

计算公式为：

gama以及beta需要在归一化的时候参与计算。其中gama为1beta默认为0所以默认归一化计算为（x-均值）/方差