ConvTranspose3d

ConvTranspose3d(in_channels, out_channels, kernel_size, stride=1, padding=0, output_padding=0, groups=1, bias=True, dilation=1, padding_mode="zeros", device=None, dtype=None, *, activation=None)

A 3-d transposed convolution over channels-last ``[batch, depth,
height, width, in_channels]`` input; weight ``[in_channels, kd, kh, kw,
out_channels // groups]``. Every knob takes an int or a triple.