Applies a 3D transposed convolution operator over an input image composed of several input planes.
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"
)(int): Number of channels in the input image
(int): Number of channels produced by the convolution
(int or tuple): Size of the convolving kernel
(int or tuple, optional): Stride of the convolution. Default: 1
(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
(int or tuple, optional): Additional size added to one side of each dimension in the output shape. Default: 0
(int, optional): Number of blocked connections from input channels to output channels. Default: 1
(bool, optional): If True, adds a learnable bias to the output. Default: True
(int or tuple, optional): Spacing between kernel elements. Default: 1
(string, optional): 'zeros', 'reflect', 'replicate' or 'circular'. Default: 'zeros'
Input: \((N, C_{in}, D_{in}, H_{in}, W_{in})\)
Output: \((N, C_{out}, D_{out}, H_{out}, W_{out})\) where $$ D_{out} = (D_{in} - 1) \times \mbox{stride}[0] - 2 \times \mbox{padding}[0] + \mbox{dilation}[0] \times (\mbox{kernel\_size}[0] - 1) + \mbox{output\_padding}[0] + 1 $$ $$ H_{out} = (H_{in} - 1) \times \mbox{stride}[1] - 2 \times \mbox{padding}[1] + \mbox{dilation}[1] \times (\mbox{kernel\_size}[1] - 1) + \mbox{output\_padding}[1] + 1 $$ $$ W_{out} = (W_{in} - 1) \times \mbox{stride}[2] - 2 \times \mbox{padding}[2] + \mbox{dilation}[2] \times (\mbox{kernel\_size}[2] - 1) + \mbox{output\_padding}[2] + 1 $$
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
\(k = \frac{groups}{C_{\mbox{out}} * \prod_{i=0}^{2}\mbox{kernel\_size}[i]}\)
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 dimensions
a 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
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)
}
}
Run the code above in your browser using DataLab