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,.,.) = 
#>  -2.0469  6.8965  2.2824  0.7413 -1.7839
#>   2.6364 -0.6391  3.7199  6.0697  4.2116
#>  -0.0825  0.3471  5.1797 -1.5637 -2.4511
#>  -0.9958 -6.2406 -1.1302  7.3218 -4.8061
#>   3.1420  5.6589  1.1481 -3.4635 -4.3349
#> 
#> (1,2,.,.) = 
#>  -0.0625  9.7216 -0.8842 -1.4253 -5.7067
#>  -3.0789 -5.8568  5.8401 -9.1868  9.1566
#>  -3.4006 -18.0903 -6.0409 -0.3181 -6.7024
#>   1.5335  3.1239 -6.7233 -6.1053 -1.5695
#>   3.3702 -1.5255  7.5491  2.2492  4.7114
#> 
#> (1,3,.,.) = 
#>    2.0660  -1.3346  -7.2633   9.9080   1.9119
#>   -3.9492   3.4750  -0.8488   1.0503  -2.8849
#>    4.4364  11.8931   2.1887  -2.0250  -8.6386
#>   -5.0817   5.7824  -1.2759   2.9925   1.5391
#>   -0.4887  -1.7196  -1.2222   1.6082  -5.2522
#> 
#> (1,4,.,.) = 
#>  -5.4745  9.8597 -1.2085  3.5830 -6.7843
#>   1.0956 -0.8899 -1.3172 -6.3585  4.0398
#>   0.7158 -0.2060 -5.1184  0.9738 -4.9517
#>   6.7638  2.7534 -1.4643  1.9107 -1.9628
#>   1.4582 -6.6380 -0.9650  7.7854  2.0511
#> 
#> (1,5,.,.) = 
#>   1.7293  3.8884 -9.8820 -1.9416  0.9031
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]