ShapeNormalizationBlock¶
-
class
maze.perception.blocks.shape_normalization.
ShapeNormalizationBlock
(*args: Any, **kwargs: Any)¶ Perception block normalizing the input and de-normalizing the output tensor dimensions.
Examples where this interface needs to be implemented are Dense Layers (batch-dim, feature-dim) or Convolution Blocks (batch-dim, feature-dim, row-dim, column-dim)
- Parameters
in_keys – Keys identifying the input tensors.
out_keys – Keys identifying the output tensors.
in_shapes – List of input shapes.
in_num_dims – Required number of dimensions for corresponding input.
out_num_dims – Required number of dimensions for corresponding output.
-
forward
(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]¶ (overrides
PerceptionBlock
)implementation of
PerceptionBlock
interface
-
abstract
normalized_forward
(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]¶ Shape normalized forward pass called in the actual forward pass of this block.
- Parameters
block_input – The block’s shape normalized input dictionary.
- Returns
The block’s shape normalized output dictionary.