Struct Conv3d 

pub struct Conv3d<D: Dtype, IT, OT, const RANK: usize> {
    pub in_channels: usize,
    pub out_channels: usize,
    pub kernel_d: usize,
    pub kernel_h: usize,
    pub kernel_w: usize,
    pub stride_d: usize,
    pub stride_h: usize,
    pub stride_w: usize,
    pub padding_d: usize,
    pub padding_h: usize,
    pub padding_w: usize,
    pub has_bias: bool,
    /* private fields */
}

3-D convolution layer: output = conv3d(input, weight) [+ b]

Input shape: [N, C_in, D_in, H_in, W_in ] Output shape: [N, C_out, D_out, H_out, W_out]

Fields

in_channels: usize

Number of input channels.

out_channels: usize

Number of output channels.

kernel_d: usize

Convolution kernel depth.

kernel_h: usize

Convolution kernel height.

kernel_w: usize

Convolution kernel width.

stride_d: usize

Stride along the depth dimension.

stride_h: usize

Stride along the height dimension.

stride_w: usize

Stride along the width dimension.

padding_d: usize

Zero-padding along the depth dimension.

padding_h: usize

Zero-padding along the height dimension.

padding_w: usize

Zero-padding along the width dimension.

has_bias: bool

Whether to add a learned bias.

Implementations

impl<D: Dtype, IT, OT, const RANK: usize> Conv3d<D, IT, OT, RANK>

pub fn new( in_channels: usize, out_channels: usize, kernel_size: (usize, usize, usize), stride: (usize, usize, usize), padding: (usize, usize, usize), has_bias: bool, ) -> Self

Creates a new Conv3d layer.

Trait Implementations

impl<D: Dtype, IT: Tensor<D, RANK> + EagerTensor, OT: Tensor<D, RANK>, const RANK: usize> Layer<IT> for Conv3d<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 Conv3d<D, SymTensor, SymTensor, RANK>

type Output = SymTensor

This layer’s output type.

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

Applies this layer to input.