op_batch_normalization: Batch Normalization

In Microsoft/CNTK-R: R Interface to the Microsoft Cognitive Toolkit (CNTK)

Description

Normalizes layer outputs for every minibatch for each output (feature) independently and applies affine transformation to preserve representation of the layer.

Usage

op_batch_normalization(operand, scale, bias, running_mean, running_inv_std,
  spatial, normalization_time_constant = 5000, blent_time_constant = 0,
  epsilon = 1e-05, use_cudnn_engine = FALSE, name = "",
  running_count = NULL)

Arguments

bias	(bool) – whether to include bias
epsilon	(float, default 0.00001) - added to avoid division by 0
name	(str) the name of the Function instance in the network
running_count

Microsoft/CNTK-R documentation built on May 28, 2019, 1:52 p.m.