ResBlockBottleneck

class torchelie.nn.ResBlockBottleneck(in_channels: int, out_channels: int, stride: int = 1)

A Residual Block. Skip connection will be added if the number of input and output channels don’t match or stride > 1 is used.

Parameters
  • in_ch (int) – input channels

  • out_ch (int) – output channels

  • stride (int) – stride

condition(z: torch.Tensor)None
forward(x: torch.Tensor, z: Optional[torch.Tensor] = None)torch.Tensor
remove_batchnorm()torchelie.nn.resblock.ResBlockBottleneck
resnext()torchelie.nn.resblock.ResBlockBottleneck
upsample_instead()torchelie.nn.resblock.ResBlockBottleneck
use_se()torchelie.nn.resblock.ResBlockBottleneck
wide(divisor: int = 2)torchelie.nn.resblock.ResBlockBottleneck
training: bool