torch: nnf_instance_norm – R documentation

Pricing

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

Get Started for Free

Documentation

torch

nnf_instance_norm

Instance_norm

Description

Applies Instance Normalization for each channel in each data sample in a batch.

Usage

nnf_instance_norm(
  input,
  running_mean = NULL,
  running_var = NULL,
  weight = NULL,
  bias = NULL,
  use_input_stats = TRUE,
  momentum = 0.1,
  eps = 1e-05
)

Arguments

`input`	the input tensor
`running_mean`	the running_mean tensor
`running_var`	the running var tensor
`weight`	the weight tensor
`bias`	the bias tensor
`use_input_stats`	whether to use input stats
`momentum`	a double for the momentum
`eps`	an eps double for numerical stability

torch

Tensors and Neural Networks with 'GPU' Acceleration

v0.3.0

MIT + file LICENSE

Authors

Daniel Falbel [aut, cre, cph], Javier Luraschi [aut], Dmitriy Selivanov [ctb], Athos Damiani [ctb], Christophe Regouby [ctb], Krzysztof Joachimiak [ctb], RStudio [cph]

Initial release

nnf_instance_norm

Description

Usage

Arguments

torch

We don't support your browser anymore