# Conv3d¶

class dragon.vm.torch.nn.Conv3d(
in_channels,
out_channels,
kernel_size,
stride=1,
dilation=1,
groups=1,
bias=True
)[source]

Apply the 3d convolution.

This module excepts the input size $$(N, C_{\text{in}}, D, H, W)$$, and output size is $$(N, C_{\text{out}}, D_{\text{out}}, H_{\text{out}}, W_{\text{out}})$$, where $$N$$ is the batch size, $$C$$ is the number of channels, $$D$$, $$H$$ and $$W$$ are the depth, height and width of data.

Examples:

m = torch.nn.Conv3d(2, 3, 3, padding=1)
x = torch.ones(2, 2, 2, 2, 2)
y = m(x)


## __init__¶

Conv3d.__init__(
in_channels,
out_channels,
kernel_size,
stride=1,
dilation=1,
groups=1,
bias=True
)[source]

Create a Conv3d module.

Parameters:
• in_channels (int) – The number of input channels.
• out_channels (int) – The number of output channels.
• kernel_size (Union[int, Sequence[int]]) – The size of convolution window.
• stride (Union[int, Sequence[int]], optional, default=1) – The stride of convolution window.