Conv1d — torch_conv1d • torch

Conv1d

Usage

torch_conv1d(
  input,
  weight,
  bias = list(),
  stride = 1L,
  padding = 0L,
  dilation = 1L,
  groups = 1L
)

Arguments

input: input tensor of shape $(minibatch, in\_channels, i W)$
weight: filters of shape $(out\_channels, \frac{in\_channels}{groups}, k W)$
bias: optional bias of shape $(out\_channels)$ . Default: NULL
stride: the stride of the convolving kernel. Can be a single number or a one-element tuple (sW,). Default: 1
padding: implicit paddings on both sides of the input. Can be a single number or a one-element tuple (padW,). Default: 0
dilation: the spacing between kernel elements. Can be a single number or a one-element tuple (dW,). Default: 1
groups: split input into groups, $in\_channels$ should be divisible by the number of groups. Default: 1

conv1d(input, weight, bias=NULL, stride=1, padding=0, dilation=1, groups=1) -> Tensor

Applies a 1D convolution over an input signal composed of several input planes.

See nn_conv1d() for details and output shape.

Examples

if (torch_is_installed()) {

filters = torch_randn(c(33, 16, 3))
inputs = torch_randn(c(20, 16, 50))
nnf_conv1d(inputs, filters)
}
#> torch_tensor
#> (1,.,.) = 
#>  Columns 1 to 6  3.3138e+00  5.2831e+00 -3.6100e-01  8.5751e+00 -7.5582e+00  7.1657e+00
#>  -6.9027e-01  1.0045e+01  3.5643e+00 -2.7117e+00 -7.2237e-01 -3.9413e+00
#>   1.1112e+01 -7.6729e+00  3.3359e+00  4.4755e+00  2.5863e+00 -6.0993e+00
#>  -1.1272e+01  1.9350e+00  6.5178e+00  1.3242e+00 -6.5695e+00 -1.0605e+00
#>   8.6817e+00  9.3736e+00 -5.6530e+00 -1.1066e+01  4.3468e+00  3.0705e+00
#>   1.5094e+01 -5.8340e+00 -6.4525e+00  1.7200e+01 -7.3534e+00 -3.9700e+00
#>  -4.3259e+00  4.0588e+00 -5.6747e+00  9.9656e+00 -4.5051e-01 -4.0336e+00
#>  -1.0973e+00  2.1664e+00 -9.0107e+00 -1.5702e+00  8.0957e+00 -4.6894e+00
#>  -8.2211e+00  6.2246e+00 -3.6846e+00  6.7496e+00  1.4534e+01 -2.1186e+00
#>   4.8683e+00  7.7937e+00 -3.0392e+00 -2.0859e+00 -3.4783e+00  1.8398e+00
#>   9.2526e+00 -4.6622e+00 -1.0056e+00  1.4893e+00  3.3024e-03  1.2059e+00
#>  -6.1647e+00 -9.8327e-02 -1.7899e+00 -3.9404e+00 -1.0753e+01  4.9760e+00
#>  -4.2930e+00  5.9204e+00  1.0420e+01  9.3273e+00  9.4540e+00 -9.5593e+00
#>  -9.1599e+00  6.2520e+00  8.3160e+00  4.2140e+00  6.4604e+00  2.3919e+01
#>   3.1060e-01  1.1038e+01 -9.5605e+00  6.7080e-01 -5.4680e+00  2.9316e+00
#>  -4.0572e+00  5.7505e-01  1.8635e+01 -9.0718e+00  3.1621e+00 -5.0485e+00
#>   1.0224e+01 -3.7857e+00 -1.2988e+00  2.4912e-01  1.3080e+00  5.7272e+00
#>   5.4048e+00 -2.6134e+00  6.2623e+00 -6.5883e+00  2.9521e+00  5.3387e+00
#>   1.4152e+00  1.9596e+00  6.5169e+00  2.9685e+00 -5.4254e+00 -2.1582e+00
#>   7.5147e+00 -1.5426e+01  9.7988e+00  8.8575e+00 -5.3817e+00 -1.4181e+00
#>  -1.5920e+00  5.7191e-01  5.1648e+00 -7.4741e+00 -2.2688e+00  2.8646e-01
#>   9.2518e+00  6.1289e-01 -3.4668e-01  7.0295e+00 -1.6571e+01 -2.4456e+00
#>   6.0348e+00  3.6638e+00  1.7295e+00 -5.4043e+00  2.4957e+00  2.2121e+00
#>   1.1415e+01  2.8437e+00 -3.2786e+00 -7.4129e+00  6.3505e+00 -4.5731e+00
#>  -6.6319e+00 -3.9537e-01  3.8207e+00 -8.5019e+00 -4.9140e+00  6.0571e+00
#>   1.6972e+00 -2.2713e+00 -1.0640e+01 -1.9947e+00  1.4233e+01  8.1856e+00
#>  -8.4049e+00  1.3405e+00  9.9549e+00 -4.3117e+00 -9.1328e+00 -5.1785e+00
#>  -8.6204e+00  1.2829e+01 -4.5831e+00 -2.1847e+00 -3.1013e+00  7.5992e-01
#>   8.0891e+00  1.2587e+01  3.6894e+00  7.1494e+00  3.7426e+00  4.3475e+00
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{20,33,48} ]