Transposed convolution / FCN upsampling (Geron Ch 14, morie.fn grfcn)

Usage

morie_geron_fcn_upsample(X, W, stride = 2)

Arguments

X: (H, W) input map.
W: (kh, kw) kernel.
stride: Positive integer.

Value

List with output, output_shape, contribution_counts, uniform_coverage, upsample_factor.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
morie_geron_fcn_upsample(V, V)
#> $output
#>      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13] [,14]
#> [1,]    1    2    5    8   14   20   30   40   46    60    62    80    78   100
#>      [,15] [,16] [,17] [,18] [,19] [,20] [,21] [,22]
#> [1,]    94   120   101   122    89   104    56    64
#> 
#> $output_shape
#> [1]  1 22
#> 
#> $contribution_counts
#>      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13] [,14]
#> [1,]    1    1    2    2    3    3    4    4    4     4     4     4     4     4
#>      [,15] [,16] [,17] [,18] [,19] [,20] [,21] [,22]
#> [1,]     4     4     3     3     2     2     1     1
#> 
#> $uniform_coverage
#> [1] FALSE
#> 
#> $upsample_factor
#> [1] 2.75
#> 
#> $stride
#> [1] 2
#> 
#> $estimate
#>      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13] [,14]
#> [1,]    1    2    5    8   14   20   30   40   46    60    62    80    78   100
#>      [,15] [,16] [,17] [,18] [,19] [,20] [,21] [,22]
#> [1,]    94   120   101   122    89   104    56    64
#> 
#> $n
#> [1] 22
#>