DDPM simplified noise-prediction loss (Geron Ch 18, morie.fn grdpml) — morie_geron_ddpm_simple_loss • rmorie

DDPM simplified noise-prediction loss (Geron Ch 18, morie.fn grdpml)

Usage

morie_geron_ddpm_simple_loss(eps, eps_pred, reduction = "mean")

Arguments

eps, eps_pred: Numeric matrices of equal shape (vectors = 1 row).
reduction: "mean" or "sum"; selects estimate only.

Value

List with loss, sum_squared_error, per_sample, residual, rmse.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
morie_geron_ddpm_simple_loss(V, V)
#> $loss
#> [1] 0
#> 
#> $sum_squared_error
#> [1] 0
#> 
#> $per_sample
#> [1] 0
#> 
#> $residual
#>      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
#> [1,]    0    0    0    0    0    0    0    0
#> 
#> $rmse
#> [1] 0
#> 
#> $estimate
#> [1] 0
#> 
#> $n
#> [1] 1
#>