Struct PoolConfig 

pub struct PoolConfig {
    pub kernel_size: Vec<usize>,
    pub stride: Vec<usize>,
    pub padding: Vec<usize>,
    pub ceil_mode: bool,
}

Pooling configuration specifying kernel size, stride, padding, and rounding mode.

Fields

kernel_size: Vec<usize>

Kernel (window) size for each spatial dimension.

stride: Vec<usize>

Stride for each spatial dimension. If empty, defaults to kernel_size.

padding: Vec<usize>

Zero-padding on each side for each spatial dimension.

ceil_mode: bool

Use ceil instead of floor for output size computation.

Implementations

impl PoolConfig

pub fn new(kernel_size: Vec<usize>) -> Self

Create a new config with the given kernel size, stride equal to kernel size, zero padding, and floor mode.

pub fn with_stride(self, stride: Vec<usize>) -> Self

Set the stride (builder pattern).

pub fn with_padding(self, padding: Vec<usize>) -> Self

Set the padding (builder pattern).

pub fn with_ceil_mode(self, ceil: bool) -> Self

Set ceil mode (builder pattern).

pub fn output_size(&self, input_size: usize, dim: usize) -> usize

Compute the output size for one spatial dimension.

Formula: floor((input + 2*padding - kernel) / stride) + 1 (or ceil if ceil_mode is true).

pub fn validate(&self) -> Result<(), PoolingError>

Validate the config, returning an error if any field is invalid.

pub fn num_spatial_dims(&self) -> usize

Number of spatial dimensions this config covers.

Trait Implementations

impl Clone for PoolConfig

fn clone(&self) -> PoolConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PoolConfig

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

Formats the value using the given formatter.