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,.,.) = 
#>   -5.5720   2.3667  -7.3122   1.8423  -7.2982
#>  -15.0026  11.1871   7.9955   1.8424   2.3371
#>   -2.8116 -17.4704   2.5230   5.1196  -5.6054
#>   -1.4614  -6.1795   3.9634  12.5255  -2.1163
#>    1.1044   2.6077   6.8300 -12.8440   4.9745
#> 
#> (1,2,.,.) = 
#>  -4.6798  5.5129 -12.2860  6.4341 -2.4183
#>   0.9886 -0.3579 -4.6331  0.4319 -10.0591
#>   8.2584 -1.5428 -3.7279 -1.1404 -0.7823
#>   5.4069 -0.9679  4.2820  1.0843 -4.3021
#>   3.5690 -8.6112  3.1458  2.1084 -5.5530
#> 
#> (1,3,.,.) = 
#>   -5.4202   6.6819  -3.9673  -4.9739   4.2795
#>    2.0982   5.8091  20.1453  -1.4443  -0.1709
#>    9.0929 -10.6066  -1.4184   1.1135 -10.7833
#>    3.6100   1.2725  -2.3199  -3.6965   5.1756
#>   -8.0629   2.0840  -5.6910  -7.6491   0.0520
#> 
#> (1,4,.,.) = 
#>   3.8247  4.7236  0.1842 -7.6635  3.5985
#>  -1.5089  4.0684  0.9608 -1.9337  4.4149
#>   1.0806  0.9685 -1.0243  1.9039 -5.8585
#>  -2.3477  0.9794 -3.2845 -5.9761  2.3310
#>  -3.2551 -7.3461 -7.7944 -5.4622 -4.7882
#> 
#> (1,5,.,.) = 
#>   -1.2285  -1.5449  -3.6510  -9.1239   7.4963
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]