torch (version 0.0.2)

torch_conv_transpose2d: Conv_transpose2d

Description

Conv_transpose2d

Arguments

input

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

weight

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

bias

NA optional bias 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 dilation * (kernel_size - 1) - padding zero-padding will be added to both sides of each dimension in the input. Can be a single number or a tuple (padH, padW). Default: 0

output_padding

NA additional size added to one side of each dimension in the output shape. Can be a single number or a tuple (out_padH, out_padW). Default: 0

groups

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

dilation

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

conv_transpose2d(input, weight, bias=None, stride=1, padding=0, output_padding=0, groups=1, dilation=1) -> Tensor

Applies a 2D transposed convolution operator over an input image composed of several input planes, sometimes also called "deconvolution".

See ~torch.nn.ConvTranspose2d for details and output shape.

.. include:: cudnn_deterministic.rst

Examples

# NOT RUN {
if (torch_is_installed()) {

# With square kernels and equal stride
inputs = torch_randn(c(1, 4, 5, 5))
weights = torch_randn(c(4, 8, 3, 3))
nnf_conv_transpose2d(inputs, weights, padding=1)
}
# }