---
title: "batchNorm"
sidebar_label: "batchNorm"
description: "Kotlin binding reference: batchNorm."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

//[clika-runtime](../../../index.md)/[io.clika.runtime](../index.md)/[Ops](index.md)/[batchNorm](batchNorm.md)

# batchNorm

[common]\
fun [batchNorm](batchNorm.md)(input: [Tensor](../Tensor/index.md), weight: [Tensor](../Tensor/index.md)? = null, bias: [Tensor](../Tensor/index.md)? = null, runningMean: [Tensor](../Tensor/index.md)? = null, runningVar: [Tensor](../Tensor/index.md)? = null, eps: [Double](https://kotlinlang.org/api/core/kotlin-stdlib/kotlin/-double/index.html)? = null, activation: [Activation](../Activation/index.md)? = null): [Tensor](../Tensor/index.md)

`batchNorm(input: Tensor, weight: Tensor? = null, bias: Tensor? = null, runningMean: Tensor? = null, runningVar: Tensor? = null, eps: Double? = null, activation: Activation? = null)`: the `batch_norm` operator. Per-channel batch normalization (inference form), channels-last. `input` is `[N, *spatial, C]`; every operand is per-channel `[C]`. The supplied `running_mean` / `running_var` ARE the statistics (inference only; no training mode, no momentum). Optional fused `activation` applies to the result.