DenseBlock¶
-
class
maze.perception.blocks.feed_forward.dense.
DenseBlock
(*args: Any, **kwargs: Any)¶ A block containing multiple subsequent dense layers. The block expects the input tensors to have the from (batch-dim, feature-dim).
- Parameters
in_keys – One key identifying the input tensors.
out_keys – One key identifying the output tensors.
in_shapes – List of input shapes.
hidden_units – List containing the number of hidden units for hidden layers.
non_lin – The non-linearity to apply after each layer.
-
build_layer_dict
() → collections.OrderedDict¶ Compiles a block-specific dictionary of network layers. This could be overwritten by derived layers (e.g. to get a ‘BatchNormalizedDenseBlock’).
- Returns
Ordered dictionary of torch modules [str, nn.Module]
-
normalized_forward
(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]¶ (overrides
ShapeNormalizationBlock
)implementation of
ShapeNormalizationBlock
interface