Struct RandomCrop 

pub struct RandomCrop { /* private fields */ }

Random crop transformation

Randomly crops a rectangular region from the input tensor. Useful for data augmentation and creating fixed-size inputs from variable-size images.

Implementations

impl RandomCrop

pub fn new(size: (usize, usize)) -> Self

Create a new random crop transform

Arguments

• size - Target crop size as (height, width)

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

Set padding to apply before cropping

Arguments

• padding - Number of pixels to pad on all sides

Trait Implementations

impl Clone for RandomCrop

fn clone(&self) -> RandomCrop

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RandomCrop

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

Formats the value using the given formatter.

impl<T: TensorElement> Transform<Tensor<T>> for RandomCrop

type Output = Tensor<T>

fn transform(&self, input: Tensor<T>) -> Result<Self::Output>

Apply the transformation to the input

fn is_deterministic(&self) -> bool

Check if the transform is deterministic