做tf.nn公司.l2_损失和tf.contrib.layers公司.l2_正则化器用于在tensorflow中添加l2正则化的相同目的？

Question

张量流中的L2正则化似乎可以通过两种方式实现：

（一）使用tf.nn公司.l2_丢失或 （二）使用tf.contrib.layers公司.l2_正则化器

这两种方法的目的是否相同？如果他们不同，他们有什么不同？在

Answer 1

他们做同样的事情（至少现在）。唯一的区别是tf.contrib.layers.l2_regularizer将tf.nn.l2_loss的结果乘以scale。

看看tf.contrib.layers.l2_regularizer[https://github.com/tensorflow/tensorflow/blob/r1.1/tensorflow/contrib/layers/python/layers/regularizers.py]的实现：

def l2_regularizer(scale, scope=None):
  """Returns a function that can be used to apply L2 regularization to weights.
  Small values of L2 can help prevent overfitting the training data.
  Args:
    scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.
    scope: An optional scope name.
  Returns:
    A function with signature `l2(weights)` that applies L2 regularization.
  Raises:
    ValueError: If scale is negative or if scale is not a float.
  """
  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % (scale,))
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g.' %
                       scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _: None

  def l2(weights):
    """Applies l2 regularization to weights."""
    with ops.name_scope(scope, 'l2_regularizer', [weights]) as name:
      my_scale = ops.convert_to_tensor(scale,
                                       dtype=weights.dtype.base_dtype,
                                       name='scale')
      return standard_ops.multiply(my_scale, nn.l2_loss(weights), name=name)

  return l2

您感兴趣的线路是：

^{pr2}$

所以在实践中，tf.contrib.layers.l2_regularizer在内部调用tf.nn.l2_loss，并简单地将结果乘以scale参数。