DepthwiseConv2d¶
- class
dragon.vm.torch.nn.
DepthwiseConv2d
(
in_channels,
out_channels,
kernel_size,
stride=1,
padding=0,
dilation=1,
bias=True
)[source]¶ Apply the 2d depthwise convolution.
Examples:
m = torch.nn.DepthwiseConv2d(3, 3, 3, padding=1) x = torch.ones(2, 3, 4, 4) y = m(x)
__init__¶
DepthwiseConv2d.
__init__
(
in_channels,
out_channels,
kernel_size,
stride=1,
padding=0,
dilation=1,
bias=True
)[source]¶Create a
DepthwiseConv2d
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.
- padding (Union[int, Sequence[int]], optional, default=0) – The zero padding size.
- dilation (Union[int, Sequence[int]], optional, default=1) – The rate of dilated kernel.
- bias (bool, optional, default=True) – Add a bias tensor to output or not.