Conv2d

Conv2d

Usage

torch_conv2d(
  input,
  weight,
  bias = list(),
  stride = 1L,
  padding = 0L,
  dilation = 1L,
  groups = 1L
)

Arguments

input

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

weight

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

bias

optional bias tensor 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

implicit paddings on both sides of the input. Can be a single number or a tuple (padH, padW). Default: 0

dilation

the spacing between kernel elements. Can be a single number or a tuple (dH, dW). Default: 1

groups

split input into groups, \(\mbox{in\_channels}\) should be divisible by the number of groups. Default: 1

conv2d(input, weight, bias=NULL, stride=1, padding=0, dilation=1, groups=1) -> Tensor

Applies a 2D convolution over an input image composed of several input planes.

See nn_conv2d() for details and output shape.

Examples

if (torch_is_installed()) {

# With square kernels and equal stride
filters = torch_randn(c(8,4,3,3))
inputs = torch_randn(c(1,4,5,5))
nnf_conv2d(inputs, filters, padding=1)
}
#> torch_tensor
#> (1,1,.,.) = 
#>   -1.6762  -1.4722  -1.6436   4.5126  -2.3594
#>   -6.1267  -0.6607   0.5919   9.5704  -3.9356
#>   -1.7615   6.3741  -2.8814   1.8651   2.6326
#>   -3.0181   6.3555  10.1203  -8.3985  -4.0173
#>    4.3111  -0.7174   2.8917  -3.1391  -8.9127
#> 
#> (1,2,.,.) = 
#>    8.9800   1.7654   7.7636  -6.3208  -8.4194
#>    5.8093   6.0707   9.6270  -3.9311   1.4963
#>   11.6820  -7.1384 -13.1026   0.6878   2.1252
#>   -2.5556  -5.7388   4.2203  -0.1439   0.9164
#>   -1.1838  -2.2137  -5.6184  -1.2443   0.6594
#> 
#> (1,3,.,.) = 
#>   0.7132  0.6092 -5.2210  7.3686  1.3817
#>  -0.1427  3.6031 -8.0537  2.5274 -4.5634
#>   4.1523  2.8623 -1.0692 -6.0115 -5.0826
#>   3.1303 -2.6635  0.9652 -4.9996 -1.5039
#>   4.5513 -6.7425  5.8636  0.2757 -5.1578
#> 
#> (1,4,.,.) = 
#>   -1.9208   7.2958   1.0516   2.1344   0.6837
#>    1.1177   2.2499   3.0147  -1.1611  -3.3016
#>   -3.3033  13.4223   2.4072  -9.5020   0.6424
#>    5.1416  -0.7583  -7.2147   8.3988   3.6592
#>   -1.6494   1.9372  -3.8303  -5.4349  -1.8648
#> 
#> (1,5,.,.) = 
#>   3.0466 -6.5147  2.8607 -4.0111  1.6115
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]