Struct LpPool2d 

pub struct LpPool2d<D: Dtype, IT, OT, const RANK: usize> {
    pub kernel_h: usize,
    pub kernel_w: usize,
    pub stride_h: usize,
    pub stride_w: usize,
    pub p: f64,
    /* private fields */
}

2-D power-average (Lp) pooling: like average pooling, generalized to an arbitrary p-norm.

Fields

kernel_h: usize

Pooling window height.

kernel_w: usize

Pooling window width.

stride_h: usize

Vertical stride.

stride_w: usize

Horizontal stride.

p: f64

The p in the p-norm.

Implementations

impl<D: Dtype, IT, OT, const RANK: usize> LpPool2d<D, IT, OT, RANK>

pub fn new(kernel_size: (usize, usize), stride: (usize, usize), p: f64) -> Self

Creates a new layer with the given kernel size, stride, and p-norm.

Trait Implementations

impl<D: Dtype, IT: Tensor<D, RANK> + EagerTensor, OT: Tensor<D, RANK>, const RANK: usize> Layer<IT> for LpPool2d<D, IT, OT, RANK>

type Output = OT

This layer’s output type.

fn call(&self, _input: IT) -> Self::Output

Applies this layer to input.

impl<D: Dtype, const RANK: usize> Layer<SymTensor> for LpPool2d<D, SymTensor, SymTensor, RANK>

type Output = SymTensor

This layer’s output type.

fn call(&self, input: SymTensor) -> SymTensor

Applies this layer to input.