class torchelie.nn.AutoGANGenBlock(in_ch: int, out_ch: int, skips_ch: List[int], ks: int = 3, mode: str = 'nearest')

A block of the generator discovered by AutoGAN.

  • in_ch (int) – number of input channels

  • out_ch (int) – number of output channels

  • skips_ch (list of int) – a list with one element per incoming skip connection. Each element is the number of channels of the incoming skip connection.

  • ks (int) – kernel size of the convolutions

  • mode (str) – usampling mode, ‘nearest’ or ‘bilinear’

forward(x: torch.Tensor, skips: List[torch.Tensor] = [])Tuple[torch.Tensor, torch.Tensor]

Forward pass

  • x (tensor) – input tensor

  • skips (list of tensor) – a tensor per incoming skip connection


output tensor, intermediate value to use in the next block’s skip


training: bool