rs_fold: Row Space Folding of 2D DelayedArray

In rikenbit/DelayedTensor: R package for sparse and out-of-core arithmetic and decomposition of Tensor

Row Space Folding of 2D DelayedArray

Description

The inverse operation to rs_unfold.

Usage

rs_fold(mat, m = NULL, modes = NULL)

## S4 method for signature 'DelayedArray'
rs_fold(mat, m, modes)

Arguments

mat	DelayedArray object (only 2D)
m	the mode corresponding to rs_unfold
modes	the original modes of the DelayedArray

Details

This function is an extension of the rs_fold by DelayedArray.

This is a wrapper function to fold.

Value

DelayedArray (higher than 2D)

References

T. Kolda, B. Bader, "Tensor decomposition and applications". SIAM Applied Mathematics and Applications 2009.

See Also

fold, rs_unfold

Examples

library("DelayedRandomArray")
darr <- RandomUnifArray(c(2,3,4))
matT2 <- rs_unfold(darr, m=2)
identical(
    as.array(rs_fold(matT2, m=2, modes=c(2,3,4))),
    as.array(darr))

rikenbit/DelayedTensor documentation built on Sept. 28, 2024, 5:43 a.m.