ModulatedConv¶
-
class
torchelie.nn.
ModulatedConv
(in_channels: int, noise_channels: int, *args, demodulate: bool = True, gain: float = 1, **kwargs)¶ -
condition
(z: torch.Tensor) → None¶
-
forward
(x: torch.Tensor, z: Optional[torch.Tensor] = None) → torch.Tensor¶
-
to_equal_lr
(leak: float = 0.2) → torchelie.nn.layers.ModulatedConv¶
-
bias
: Optional[torch.Tensor]¶
-
dilation
: Tuple[int, …]¶
-
groups
: int¶
-
kernel_size
: Tuple[int, …]¶
-
out_channels
: int¶
-
output_padding
: Tuple[int, …]¶
-
padding
: Tuple[int, …]¶
-
padding_mode
: str¶
-
stride
: Tuple[int, …]¶
-
transposed
: bool¶
-
weight
: torch.Tensor¶
-