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,.,.) = 
#>    1.6393  -2.5899  -8.5067  -1.8238   4.1000
#>    2.1120  -4.1321  11.0553   3.7196   0.7362
#>   -5.2617   2.5456   3.9080  -2.5368   4.2549
#>    3.5291 -15.2413   8.2195 -11.3693   3.8103
#>    0.2621   9.5971  -0.2704   6.1829   3.7084
#> 
#> (1,2,.,.) = 
#>   0.1694 -2.0025 -8.5001 -1.3313 -0.2288
#>  -2.2929  2.0407 -4.5657  7.2870  1.5678
#>  -0.9393 -5.8278 -4.1736 -12.8371 -2.7586
#>  -4.2690 -9.7113  1.7583 -7.1215 -3.1604
#>  -0.0940  2.4235  1.7249 -0.8745 -0.4284
#> 
#> (1,3,.,.) = 
#>   0.0273 -2.1521 -8.8350 -8.4736 -2.5637
#>   3.0278 -3.4849  2.8462 -8.2803 -3.2730
#>  -1.9833  4.1347  3.1995 -8.7701 -8.4042
#>   8.3239 -4.1759  1.5025 -6.0144 -4.1036
#>  -2.2783  4.2398  2.8385 -1.0805  0.1099
#> 
#> (1,4,.,.) = 
#>  -1.5909  0.1692 -2.3328 -3.3655  3.3153
#>   6.5030 -14.5062  3.9954 -8.0446  6.3689
#>   6.4542 -2.9360  8.0266 -2.8897 -0.0591
#>  -0.9082  3.0974  0.4244 -1.1744  6.8117
#>  -3.8428 -9.7227  4.2513  1.6934  1.2398
#> 
#> (1,5,.,.) = 
#>   0.2714 -4.2587  0.2697 -1.6718  1.1456
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]