Applies Batch Normalization for each channel across a batch of data.
nnf_batch_norm(
input,
running_mean,
running_var,
weight = NULL,
bias = NULL,
training = FALSE,
momentum = 0.1,
eps = 1e-05
)
input tensor
the running_mean tensor
the running_var tensor
the weight tensor
the bias tensor
bool wether it's training. Default: FALSE
the value used for the running_mean
and running_var
computation.
Can be set to None for cumulative moving average (i.e. simple average). Default: 0.1
a value added to the denominator for numerical stability. Default: 1e-5