Conv_transpose2d — torch_conv_transpose2d • torch

Conv_transpose2d

Usage

torch_conv_transpose2d(
  input,
  weight,
  bias = list(),
  stride = 1L,
  padding = 0L,
  output_padding = 0L,
  groups = 1L,
  dilation = 1L
)

Arguments

input: input tensor of shape \((\mbox{minibatch} , \mbox{in\_channels} , iH , iW)\)
weight: filters of shape \((\mbox{in\_channels} , \frac{\mbox{out\_channels}}{\mbox{groups}} , kH , kW)\)
bias: optional bias of shape \((\mbox{out\_channels})\). Default: NULL
stride: the stride of the convolving kernel. Can be a single number or a tuple (sH, sW). Default: 1
padding: dilation * (kernel_size - 1) - padding zero-padding will be added to both sides of each dimension in the input. Can be a single number or a tuple (padH, padW). Default: 0
output_padding: additional size added to one side of each dimension in the output shape. Can be a single number or a tuple (out_padH, out_padW). Default: 0
groups: split input into groups, \(\mbox{in\_channels}\) should be divisible by the number of groups. Default: 1
dilation: the spacing between kernel elements. Can be a single number or a tuple (dH, dW). Default: 1

conv_transpose2d(input, weight, bias=NULL, stride=1, padding=0, output_padding=0, groups=1, dilation=1) -> Tensor

Applies a 2D transposed convolution operator over an input image composed of several input planes, sometimes also called "deconvolution".

See nn_conv_transpose2d() for details and output shape.

Examples

if (torch_is_installed()) {

# With square kernels and equal stride
inputs = torch_randn(c(1, 4, 5, 5))
weights = torch_randn(c(4, 8, 3, 3))
nnf_conv_transpose2d(inputs, weights, padding=1)
}
#> torch_tensor
#> (1,1,.,.) = 
#>  -6.3960  9.1232 -2.8004 -1.3868  1.3521
#>   1.4934  6.9319 -11.9201  6.7481  1.3496
#>  -1.8785  5.5954  3.4016  5.5397 -7.6467
#>  -1.9971  6.6623  2.2538  1.6590 -3.4015
#>  -1.4083 -0.7698  1.2899 -4.0362  6.8385
#> 
#> (1,2,.,.) = 
#>  -3.6573  0.8038 -0.9764 -4.4286 -2.6406
#>  -3.2724  1.0349  6.4589 -2.6047 -0.3668
#>   4.8154  2.5700  3.9379 -0.8989  1.1496
#>  -2.0347  2.7453  7.1114 -4.0670 -5.2499
#>  -0.4703  7.3308  2.6528  1.6839  0.5830
#> 
#> (1,3,.,.) = 
#>   5.9283 -0.5292 -8.0352  4.0898  3.5460
#>  -1.8120 -7.5394  2.6333  5.9905 -3.7589
#>  -3.2381  1.3461 -0.6741 -3.1322 -0.7111
#>   3.2499 -3.0140  0.1912 -10.1276  1.3264
#>   2.0959  0.8129 -0.2942  3.0702  2.4320
#> 
#> (1,4,.,.) = 
#>  -11.1249  -7.8550   2.3842   4.4185   3.0066
#>   -3.9357  -4.3043   2.8180   5.1852   3.9617
#>   -2.1041  -5.2036  -5.1153  -2.4998   0.3958
#>   -2.9048  -0.2169  -2.5775   5.0386  -5.3678
#>   -0.0440   1.9224   1.6378  -2.5885   0.3614
#> 
#> (1,5,.,.) = 
#>    2.6500  -0.2922   0.9965  -2.6890  -1.1816
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]