ResBlockConv

class aixd.mlmodel.architecture.blocks.ResBlockConv(*args: Any, **kwargs: Any)[source]

Bases: Module

Module implementing a convolutional residual block.

Parameters:
  • dim (int) – The number of dimensions of the input data (1, 2, or 3).

  • in_channels (int) – The number of input channels.

  • out_channels (int) – The number of output channels.

  • scaling (str) – The scaling mode to use. One of ‘down’ (reduce dimensionality), ‘up’ (increase dimensionality), or None (no change in dimensionality).

  • activation (Union[nn.Module, str]) – The activation function to use.

  • up_padding (Tuple[int]) – The padding to use for upsampling. If shape was uneven when encoding (downsampling), tensor must also be cropped to uneven when decoding (upsampling).

Methods