InferenceBlock¶
-
class
maze.perception.blocks.inference.
InferenceBlock
(*args: Any, **kwargs: Any)¶ - An inference block combining multiple perception blocks into one prediction module.
- Conditions on using the InferenceBlock object:
All keys of the perception_blocks dictionary have to be unique
All out_keys used when creating the blocks have to be unique
All block keys in the perception_blocks dict have to sub-strings of all their corresponding out_keys
The given in_keys should be a subset of the inputs of the computational graph
The given out_keys should be a subset of the outputs of the computational graph
- Parameters
in_keys – Keys identifying the input tensors.
out_keys – Keys identifying the output tensors.
in_shapes – List of input shapes.
perception_blocks – Dictionary of perception blocks.
-
forward
(block_input: Dict[str, torch.Tensor]) → Dict[str, torch.Tensor]¶ (overrides
PerceptionBlock
)implementation of
PerceptionBlock
interface