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,.,.) = 
#>    2.0231  -5.6029 -11.5761   1.7143   5.9216
#>   -8.6533  -3.1235  15.7295  -6.0593   9.2511
#>    8.4979 -13.4046 -13.9410  -9.4461   9.4648
#>   -4.4897   3.7682   0.3209   8.7378  -6.1204
#>   -0.3647   0.9731  -0.7515   3.4601   1.6865
#> 
#> (1,2,.,.) = 
#>    7.0896  -5.5982  -7.6702  -3.5603  -1.2482
#>   -8.6291   1.6284   0.6596  12.8297   7.0360
#>    0.4704  -0.7088   1.9296   0.7521   3.7638
#>    2.5873  13.8303  -1.0990  -1.3369  -6.8281
#>    1.7741   0.4981   3.9623  -2.9872  -0.7715
#> 
#> (1,3,.,.) = 
#>    1.9486   4.2593   3.4958  -4.3602 -11.2844
#>   -4.6424  -2.3620  -7.5738  -0.2210   4.9159
#>    2.8113  13.1138  13.1928  -3.5597   5.6266
#>   -4.2096  -6.5700  -8.8867   1.5816  -5.5888
#>   -0.2709  -1.5333   0.1801   0.7487  -5.4131
#> 
#> (1,4,.,.) = 
#>    2.9319  -1.7305  -3.5251   3.4202   1.0916
#>   -6.4199  -6.5232  -3.4441   3.7061  -4.2515
#>    3.5935   4.0829   0.3279  -6.4848   5.5157
#>   -3.1565 -12.9017   8.0733  -7.9554  13.5600
#>   -0.2963   2.9512   2.8726   0.0982  -0.0403
#> 
#> (1,5,.,.) = 
#>   -4.7585  10.8287   8.5631   3.2067   0.8199
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]