Struct GroupNorm 

pub struct GroupNorm<B>
where
    B: Backend,
{ /* private fields */ }

Group Normalization layer.

Examples

let gn = GroupNorm::<CpuBackend>::new(8, 32, 1e-5, DType::F64, &dev)?;
let x = CpuTensor::rand((2, 32, 16, 16), DType::F64, &dev)?;
let y = gn.forward(&x)?; // [2, 32, 16, 16]

Implementations

impl<B> GroupNorm<B>

where B: Backend,

pub fn new( num_groups: usize, num_channels: usize, eps: f64, dtype: DType, device: &<B as Backend>::Device, ) -> Result<GroupNorm<B>, Error>

Create a new GroupNorm layer.

Arguments

• num_groups: number of groups to divide channels into
• num_channels: total number of channels (must be divisible by num_groups)
• eps: numerical stability constant
• dtype: data type
• device: compute device

pub fn num_groups(&self) -> usize

pub fn num_channels(&self) -> usize

Trait Implementations

impl<B> Module<B> for GroupNorm<B>

where B: Backend,

fn forward(&self, x: &Tensor<B>) -> Result<Tensor<B>, Error>

Compute the output tensor from the input tensor. This defines the layer’s computation (forward pass).

fn parameters(&self) -> Vec<Tensor<B>>

Return all trainable parameters of this module. The optimizer uses these to update weights during training.

fn named_parameters(&self) -> Vec<(String, Tensor<B>)>

Return all trainable parameters with human-readable names.

fn set_training(&self, _training: bool)

Set training or evaluation mode.

fn is_training(&self) -> bool

Whether the module is in training mode (default: true).

fn train(&self)

Convenience: set training mode.

fn eval(&self)

Convenience: set evaluation mode.

fn num_parameters(&self) -> usize

Total number of scalar parameters in this module.

fn trainable_params_count(&self) -> usize

Number of trainable (variable) parameters.

fn frozen_parameters(&self) -> Vec<Tensor<B>>

Freeze all parameters: returns new parameter tensors with is_variable = false, preventing gradient accumulation.

fn state_dict(&self) -> Vec<(String, Tensor<B>)>

Returns a state_dict-style map of parameter name → tensor.