Struct AdaptiveAvgPool2dLayer 

pub struct AdaptiveAvgPool2dLayer { /* private fields */ }

Adaptive average pooling: output a fixed spatial size regardless of input size.

NHWC layout: [batch, H, W, C] -> [batch, out_h, out_w, C].

Implementations

impl AdaptiveAvgPool2dLayer

pub fn new(out_h: usize, out_w: usize) -> Self

pub fn output_h(&self) -> usize

pub fn output_w(&self) -> usize

pub fn forward( &self, graph: &mut Graph, input: NodeId, ) -> Result<NodeId, ModelError>

pub fn forward_inference(&self, input: &Tensor) -> Result<Tensor, ModelError>

Trait Implementations

impl Clone for AdaptiveAvgPool2dLayer

fn clone(&self) -> AdaptiveAvgPool2dLayer

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AdaptiveAvgPool2dLayer

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for AdaptiveAvgPool2dLayer

fn eq(&self, other: &AdaptiveAvgPool2dLayer) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for AdaptiveAvgPool2dLayer

impl Eq for AdaptiveAvgPool2dLayer

impl StructuralPartialEq for AdaptiveAvgPool2dLayer