MConvNormReLU¶
-
class
torchelie.nn.
MConvNormReLU
(in_ch: int, out_ch: int, ks: int, norm, center: bool = True)¶ Experimental: A packed block with Masked Conv-Norm-ReLU
- Parameters
in_ch (int) – input channels
out_ch (int) – output channels
ks (int) – kernel size
norm (ctor) – A normalization layer constructor in the form
(num_layers) -> norm layer
or Nonecenter (bool) – whether the masked conv has access to the central pixel or not
- Returns
A packed block with MaskedConv-Norm-ReLU as a CondSeq
Warning
MConvNormReLU() is experimental, and may change or be deleted soon if not already broken