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,.,.) = 
#>    0.3928  -4.3969  -2.3146   7.7619   5.4566
#>    2.8590  -1.3547   3.4482   0.3780   9.6762
#>   -2.0638   6.4916  -2.3878   0.5365   1.3308
#>    6.3936   7.2366  -4.6264  10.7481  -6.6758
#>   -0.3444  -7.9977   2.1000   7.4754   1.2675
#> 
#> (1,2,.,.) = 
#>   5.6546 -1.1660 -5.4485  7.0526 -1.5640
#>  -0.3930  2.6439 -4.3852 -0.9276 -3.5268
#>  -2.4788 -2.0740  2.4324 -1.9888 -1.8247
#>  -9.5550  0.0146  2.6103  2.4464  6.0080
#>  -1.2036 -0.3968 -8.2409 -5.0677  0.6947
#> 
#> (1,3,.,.) = 
#>   -0.8294   1.6107  -4.4979   1.0547  -1.8074
#>   -4.6571  -0.3706   4.8720  14.9730  -7.3230
#>    9.7994   2.8858  -6.0449   3.7432  -1.6568
#>   -3.1815  -1.1242  -2.3441 -10.9135   3.1649
#>   -7.2575  -0.1519   6.5451   5.3078   7.1776
#> 
#> (1,4,.,.) = 
#>   -0.8931  -0.2716   6.5106  -3.1991  -3.2743
#>   -1.6721  -5.8525   2.8246  -2.0895  -0.9239
#>   -6.7006  -1.4318   0.9618   6.6474   1.4570
#>    8.0434  -0.3249 -13.5622   6.5173  -8.2603
#>    9.8050  13.0547  -2.8967   0.6291  -0.1371
#> 
#> (1,5,.,.) = 
#>  -0.7943  4.2281  1.8168 -1.4556 -3.7774
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{1,8,5,5} ]