Function arrayfire::convolve2_nn

pub fn convolve2_nn<T>(
    signal: &Array<T>, 
    filter: &Array<T>, 
    strides: Dim4, 
    padding: Dim4, 
    dilation: Dim4
) -> Array<T> where
    T: HasAfEnum + RealFloating, 

Convolution Integral for two dimensional data

This version of convolution is consistent with the machine learning formulation that will spatially convolve a filter on 2-dimensions against a signal. Multiple signals and filters can be batched against each other. Furthermore, the signals and filters can be multi-dimensional however their dimensions must match. Usually, this is the forward pass convolution in ML

Example:

Signals with dimensions: d0 x d1 x d2 x Ns

Filters with dimensions: d0 x d1 x d2 x Nf

Resulting Convolution: d0 x d1 x Nf x Ns

Parameters

• signal is the input signal
• filter is convolution filter
• strides are distance between consecutive elements along each dimension for original convolution
• padding specifies padding width along each dimension for original convolution
• dilation specifies filter dilation along each dimension for original convolution

Return Values

Convolved Array