Applies a 3D transposed convolution operator over an input image composed of several input planes.

## Usage

```
nn_conv_transpose3d(
in_channels,
out_channels,
kernel_size,
stride = 1,
padding = 0,
output_padding = 0,
groups = 1,
bias = TRUE,
dilation = 1,
padding_mode = "zeros"
)
```

## Arguments

- in_channels
(int): Number of channels in the input image

- out_channels
(int): Number of channels produced by the convolution

- kernel_size
(int or tuple): Size of the convolving kernel

- stride
(int or tuple, optional): Stride of the convolution. Default: 1

- padding
(int or tuple, optional):

`dilation * (kernel_size - 1) - padding`

zero-padding will be added to both sides of each dimension in the input. Default: 0 output_padding (int or tuple, optional): Additional size added to one side of each dimension in the output shape. Default: 0- output_padding
(int or tuple, optional): Additional size added to one side of each dimension in the output shape. Default: 0

- groups
(int, optional): Number of blocked connections from input channels to output channels. Default: 1

- bias
(bool, optional): If

`True`

, adds a learnable bias to the output. Default:`True`

- dilation
(int or tuple, optional): Spacing between kernel elements. Default: 1

- padding_mode
(string, optional):

`'zeros'`

,`'reflect'`

,`'replicate'`

or`'circular'`

. Default:`'zeros'`

## Details

The transposed convolution operator multiplies each input value element-wise by a learnable kernel, and sums over the outputs from all input feature planes.

This module can be seen as the gradient of Conv3d with respect to its input. It is also known as a fractionally-strided convolution or a deconvolution (although it is not an actual deconvolution operation).

`stride`

controls the stride for the cross-correlation.`padding`

controls the amount of implicit zero-paddings on both sides for`dilation * (kernel_size - 1) - padding`

number of points. See note below for details.`output_padding`

controls the additional size added to one side of the output shape. See note below for details.`dilation`

controls the spacing between the kernel points; also known as the à trous algorithm. It is harder to describe, but this`link`

_ has a nice visualization of what`dilation`

does.`groups`

controls the connections between inputs and outputs.`in_channels`

and`out_channels`

must both be divisible by`groups`

. For example,At groups=1, all inputs are convolved to all outputs.

At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels, and producing half the output channels, and both subsequently concatenated.

At groups=

`in_channels`

, each input channel is convolved with its own set of filters (of size \(\left\lfloor\frac{out\_channels}{in\_channels}\right\rfloor\)).

The parameters `kernel_size`

, `stride`

, `padding`

, `output_padding`

can either be:

a single

`int`

-- in which case the same value is used for the depth, height and width dimensionsa

`tuple`

of three ints -- in which case, the first`int`

is used for the depth dimension, the second`int`

for the height dimension and the third`int`

for the width dimension

## Note

Depending of the size of your kernel, several (of the last)
columns of the input might be lost, because it is a valid `cross-correlation`

*,
and not a full cross-correlation*.
It is up to the user to add proper padding.

The `padding`

argument effectively adds `dilation * (kernel_size - 1) - padding`

amount of zero padding to both sizes of the input. This is set so that
when a `~torch.nn.Conv3d`

and a `~torch.nn.ConvTranspose3d`

are initialized with same parameters, they are inverses of each other in
regard to the input and output shapes. However, when `stride > 1`

,
`~torch.nn.Conv3d`

maps multiple input shapes to the same output
shape. `output_padding`

is provided to resolve this ambiguity by
effectively increasing the calculated output shape on one side. Note
that `output_padding`

is only used to find output shape, but does
not actually add zero-padding to output.

In some circumstances when using the CUDA backend with CuDNN, this operator
may select a nondeterministic algorithm to increase performance. If this is
undesirable, you can try to make the operation deterministic (potentially at
a performance cost) by setting `torch.backends.cudnn.deterministic = TRUE`

.

## Shape

Input: \((N, C_{in}, D_{in}, H_{in}, W_{in})\)

Output: \((N, C_{out}, D_{out}, H_{out}, W_{out})\) where $$ D_{out} = (D_{in} - 1) \times \mbox{stride}[0] - 2 \times \mbox{padding}[0] + \mbox{dilation}[0] \times (\mbox{kernel\_size}[0] - 1) + \mbox{output\_padding}[0] + 1 $$ $$ H_{out} = (H_{in} - 1) \times \mbox{stride}[1] - 2 \times \mbox{padding}[1] + \mbox{dilation}[1] \times (\mbox{kernel\_size}[1] - 1) + \mbox{output\_padding}[1] + 1 $$ $$ W_{out} = (W_{in} - 1) \times \mbox{stride}[2] - 2 \times \mbox{padding}[2] + \mbox{dilation}[2] \times (\mbox{kernel\_size}[2] - 1) + \mbox{output\_padding}[2] + 1 $$

## Attributes

weight (Tensor): the learnable weights of the module of shape \((\mbox{in\_channels}, \frac{\mbox{out\_channels}}{\mbox{groups}},\) \(\mbox{kernel\_size[0]}, \mbox{kernel\_size[1]}, \mbox{kernel\_size[2]})\). The values of these weights are sampled from \(\mathcal{U}(-\sqrt{k}, \sqrt{k})\) where \(k = \frac{groups}{C_{\mbox{out}} * \prod_{i=0}^{2}\mbox{kernel\_size}[i]}\)

bias (Tensor): the learnable bias of the module of shape (out_channels) If

`bias`

is`True`

, then the values of these weights are sampled from \(\mathcal{U}(-\sqrt{k}, \sqrt{k})\) where \(k = \frac{groups}{C_{\mbox{out}} * \prod_{i=0}^{2}\mbox{kernel\_size}[i]}\)

## Examples

```
if (torch_is_installed()) {
if (FALSE) {
# With square kernels and equal stride
m <- nn_conv_transpose3d(16, 33, 3, stride = 2)
# non-square kernels and unequal stride and with padding
m <- nn_conv_transpose3d(16, 33, c(3, 5, 2), stride = c(2, 1, 1), padding = c(0, 4, 2))
input <- torch_randn(20, 16, 10, 50, 100)
output <- m(input)
}
}
```