torch (version 0.0.2)

torch_conv2d: Conv2d

Description

Conv2d

Arguments

input

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

weight

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

bias

NA optional bias tensor of shape \((\mbox{out\_channels})\). Default: None

stride

NA the stride of the convolving kernel. Can be a single number or a tuple (sH, sW). Default: 1

padding

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

dilation

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

groups

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

conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) -> Tensor

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

See ~torch.nn.Conv2d for details and output shape.

.. include:: cudnn_deterministic.rst

Examples

# NOT RUN {
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)
}
# }