InHeadConv

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

Bases: InHead

Convolutional Network for encoding spatially strucured data in 1, 2 or 3 dimensions.

Parameters:

dim (int) – The dimensionality of the data: 1, 2 or 3.
in_shape (Tuple[int]) – The shape of the input data.
latent_dims (List[int])) – A list of integers representing the dimensions of the latent space. The length of the sequence defines the number of layers.
activation (Union[nn.Module, str]) – The activation function to use.
attn_block_indices (List[int]) – Sequence of indices where to insert an attention layer in the encoding blocks.

Methods