tannic::transformation::Convolution1D Class Reference

Expression for 1D convolution operations. More...

#include <convolutions.hpp>

Public Member Functions
constexpr type	promote (type signal, type kernel) const
	Type promotion for 1D convolution.
constexpr Shape	transform (Shape const &signal, Shape const &kernel) const
	Computes output shape for 1D convolution.
void	forward (Tensor const &signal, Tensor const &kernel, Tensor &result) const
	Performs the forward pass of 1D convolution.

Public Attributes
std::array< std::size_t, 1 >	strides
	Stride values for the convolution operation.
std::array< std::size_t, 1 >	padding
	Padding values for the convolution operation.

Detailed Description

Expression for 1D convolution operations.

Implements 1D convolution with:

• Input and kernel dtype validation
• Automatic output shape calculation
• Support for strides and padding

Member Function Documentation

forward()

void tannic::transformation::Convolution1D::forward	(	Tensor const &	signal,
		Tensor const &	kernel,
		Tensor &	result
	)		const

Performs the forward pass of 1D convolution.

Parameters

signal	Input signal tensor
kernel	Convolution kernel tensor
result	Output tensor to store convolution result

promote()

constexpr type tannic::transformation::Convolution1D::promote ( type  signal, type  kernel  ) const

inlineconstexpr

Type promotion for 1D convolution.

Requires both signal and kernel to have identical data types.

Parameters

signal	Data type of the input signal tensor
kernel	Data type of the kernel tensor

Returns

Data type (same as inputs)

Exceptions

Exception

if signal and kernel dtypes don't match

transform()

constexpr Shape tannic::transformation::Convolution1D::transform ( Shape const &  signal, Shape const &  kernel  ) const

inlineconstexpr

Computes output shape for 1D convolution.

Calculates the output shape based on input signal shape, kernel shape, strides, and padding using the standard convolution formula.

Parameters

signal	Shape of the input signal tensor (N, C_in, L_in)
kernel	Shape of the kernel tensor (C_out, K_in, K_len)

Returns

Output shape after 1D convolution (N, C_out, L_out)

Exceptions

Exception

if input ranks are not 3 or channel dimensions don't match

Expected input shapes:

• Signal: [batch_size, input_channels, signal_length]
• Kernel: [output_channels, input_channels, kernel_length]
• Output: [batch_size, output_channels, output_length]

Output length formula: L_out = (L_in + 2*padding - K_len) / stride + 1

Member Data Documentation

padding

std::array<std::size_t, 1> tannic::transformation::Convolution1D::padding

Padding values for the convolution operation.

strides

std::array<std::size_t, 1> tannic::transformation::Convolution1D::strides

Stride values for the convolution operation.

---

The documentation for this class was generated from the following file:

• include/tannic/convolutions.hpp