Skip to contents

Conv_transpose1d

Usage

torch_conv_transpose1d(
  input,
  weight,
  bias = list(),
  stride = 1L,
  padding = 0L,
  output_padding = 0L,
  groups = 1L,
  dilation = 1L
)

Arguments

input

input tensor of shape \((\mbox{minibatch} , \mbox{in\_channels} , iW)\)

weight

filters of shape \((\mbox{in\_channels} , \frac{\mbox{out\_channels}}{\mbox{groups}} , kW)\)

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 (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 (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_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 (dW,). Default: 1

conv_transpose1d(input, weight, bias=NULL, stride=1, padding=0, output_padding=0, groups=1, dilation=1) -> Tensor

Applies a 1D transposed convolution operator over an input signal composed of several input planes, sometimes also called "deconvolution".

See nn_conv_transpose1d() for details and output shape.

Examples

if (torch_is_installed()) {

inputs = torch_randn(c(20, 16, 50))
weights = torch_randn(c(16, 33, 5))
nnf_conv_transpose1d(inputs, weights)
}
#> torch_tensor
#> (1,.,.) = 
#>  Columns 1 to 8   3.1133  -4.7723  -2.3931  -5.4539  -7.1972  12.9957  13.4438   7.1489
#>   -0.4373   3.2845   6.6364  20.3117 -11.1368   4.7531  -5.1642   8.9951
#>   -0.3449   1.5255  -4.1246  -6.8116  -3.3254   1.6915  12.5595   1.8838
#>   -1.6549  -7.0034   6.1678  13.2144 -12.1304  -3.7036 -12.1988   2.7846
#>    6.4817 -11.0751   2.1542  -1.9715 -13.8498  -0.3708  26.4643   3.0109
#>   -0.7963   0.3241   5.2954  15.8373   6.9060  -4.3283  -6.1664  -8.7904
#>   -2.3767  -2.0517 -13.4455  -1.5481  12.5281  -9.5647  -1.5644 -10.5425
#>   -2.4293  11.8508  -9.4020  -3.8714  13.9610 -10.0671   2.5673   6.9445
#>   -1.1489 -10.3609   5.3897  -8.2850  13.4199   1.4482  11.7322  -0.2206
#>   -0.2007   0.1689 -14.4817  15.5031  16.2238  -6.9368  -8.7215   1.2905
#>    1.9709  -3.1902   9.5467   3.2830   6.2044 -13.3291 -11.4545   6.1785
#>   -1.6569   5.3462  -3.9712   5.0305  22.8593 -11.9518 -11.9755  15.4126
#>   -2.6268   0.6996  -3.9360  -3.9430   6.7054   0.9552  -4.0315  -0.7178
#>    5.7376  -5.0806   6.1834 -11.8485  -3.9999   5.9285  -0.9666  -0.0510
#>    0.6164  -0.2205 -15.5796  -4.0639  -5.5544  23.7233 -11.5765  -3.8040
#>    3.2813  -1.4552   3.8877   1.0882   3.8026  -6.8719   4.6076   6.2347
#>   -0.7848   0.6196   6.7321  -3.9167 -15.1159  18.6778  -0.4508  -2.6980
#>   -1.1497   3.4999 -12.8211  16.7226   5.8928  -2.0356  -4.0186 -18.9285
#>   -3.2344  -0.7106  -7.1196  15.6061  14.2163  -8.7526   2.4252   6.2051
#>    0.3937  -1.5599  -2.8903  -0.0370   2.4302  -5.0103  -6.9539  11.7354
#>   -4.9761   3.1591   2.8487  -4.1168 -12.5216 -19.1421  -0.8837  -1.6499
#>   -4.5019  -7.6711   2.8350   1.2834   0.8746  -5.2829  23.4167   6.5596
#>   -1.9298  -0.7282   8.6003 -13.8451  13.8121  11.3894  -8.6946 -16.1076
#>    1.4646   7.7329   4.4562   1.8917  12.8766  11.4385   7.3228 -20.4873
#>   -0.5677   4.7500  -4.8113  -8.5771 -10.4123  -7.8519   8.4947   0.4458
#>   -3.0359   7.6765  -1.5402 -15.9809  -9.8216  26.8429  -5.7206 -11.2942
#>    3.0253  -2.2538 -18.2349  18.0669  10.1747  -1.4759   2.4461  -7.1174
#>   -0.3862  -8.1428   4.1358  -2.3128  -0.6656  -0.7421  18.4221   5.4598
#>    3.0224  -6.4545   4.6795  -7.8754  -0.2590   6.4324 -13.1886  -3.9383
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{20,33,54} ]