Struct SparseConv1d 

pub struct SparseConv1d { /* private fields */ }

Sparse 1D Convolution layer

Implements 1D convolution operations optimized for sparse inputs and/or sparse kernels. This is particularly useful for time series data, audio processing, and NLP applications where sparsity can naturally occur or be induced through pruning.

Implementations

impl SparseConv1d

pub fn new( in_channels: usize, out_channels: usize, kernel_size: usize, stride: Option<usize>, padding: Option<usize>, dilation: Option<usize>, sparsity: f32, use_bias: bool, ) -> TorshResult<Self>

Create a new sparse 1D convolution layer

Arguments

• in_channels - Number of input channels
• out_channels - Number of output channels
• kernel_size - Convolution kernel size
• stride - Stride for convolution (default: 1)
• padding - Padding for convolution (default: 0)
• dilation - Dilation for convolution (default: 1)
• sparsity - Kernel sparsity level (0.0 = dense, 1.0 = fully sparse)
• use_bias - Whether to include learnable bias

Returns

• TorshResult<Self> - New sparse 1D convolution layer or error

Example

use torsh_sparse::nn::convolution::SparseConv1d;

// Create sparse 1D conv: 16->32 channels, kernel size 3, 80% sparse
let conv = SparseConv1d::new(16, 32, 3, None, None, None, 0.8, true).expect("valid conv1d config");

pub fn forward(&self, input: &Tensor) -> TorshResult<Tensor>

Forward pass for sparse 1D convolution

Arguments

• input - Input tensor (batch_size, in_channels, length)

Returns

• TorshResult<Tensor> - Output tensor (batch_size, out_channels, out_length)

pub fn num_parameters(&self) -> usize

Get the number of parameters

pub fn kernel_sparsity(&self) -> f32

Get kernel sparsity

pub fn in_channels(&self) -> usize

Get input channels

pub fn out_channels(&self) -> usize

Get output channels

pub fn kernel_size(&self) -> usize

Get kernel size

pub fn stride(&self) -> usize

Get stride

pub fn padding(&self) -> usize

Get padding

pub fn dilation(&self) -> usize

Get dilation

Trait Implementations

impl Clone for SparseConv1d

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SparseConv1d

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

Formats the value using the given formatter.