tf.clip_by_average_norm( t, clip_norm, name=None )
See the guide: Training > Gradient Clipping
Clips tensor values to a maximum average L2-norm.
Given a tensor
t, and a maximum clip value
clip_norm, this operation
t so that its average L2-norm is less than or equal to
clip_norm. Specifically, if the average L2-norm is already less than or
t is not modified. If the average L2-norm is
clip_norm, then this operation returns a tensor of the same
type and shape as
t with its values set to:
t * clip_norm / l2norm_avg(t)
In this case, the average L2-norm of the output tensor is
This operation is typically used to clip gradients before applying them with an optimizer.
clip_norm: A 0-D (scalar)
Tensor> 0. A maximum clipping value.
name: A name for the operation (optional).