Skip to content

helper

torch_to_nnef.op.helper

OpHelper 

OpHelper(g, node, name_to_tensor, null_ref, inference_target)
add_single_output_op_from_ir_datas 
add_single_output_op_from_ir_datas(nnef_op_type: str, input_nodes: T.List[Data], output_tensor_name_suffix: str = '', force_full_output_tensor_name: str = '', reuse_if_name_exists: bool = False, **kwargs) -> TorchOp

Use input_nodes Data instead of nnef.Tensor.

Also nnefe

OpRegistry 

OpRegistry(torch_mod_id: str)
register 
register(torch_op_ids: T.Optional[T.List[str]] = None)

By default we take the name of the function if not specified.

add_tensor_variable_node_as_nnef_tensor 

add_tensor_variable_node_as_nnef_tensor(g: NGraph, node: TensorVariable, name_to_tensor: T.Dict[str, NTensor], name_suffix: str = '', prevent_variable: bool = False, force_full_output_tensor_name: T.Optional[str] = None) -> NTensor

Create NNEF tensor and register in graph from torch_graph.Data node.

It automatically adds variable if node is a torch tensor is associated (it avoids bloating nnef graph file with matrix values)

cast_and_add_nnef_operation 

cast_and_add_nnef_operation(name_to_tensor: str, **kwargs)

Ensure to cast parameters before adding operation to NNEF graph.

cast_inputs_and_attrs 

cast_inputs_and_attrs(inputs, attrs, g, name_to_tensor)

Catch input or attr that would still be torch_graph values into NNEF.

cast_to_if_not_dtype_and_variable 

cast_to_if_not_dtype_and_variable(g, name_to_tensor, node, nnef_tensor: NTensor, cast_to: np.dtype, suffix: str = '')

Force casting not expressed in IR graph in case of div for example.

This is neccessary since tract and maybe other inference engine may not cast implicitly to float during div operation for example leading to rounding issues.

maybe_align_inputs_ranks 

maybe_align_inputs_ranks(g: NGraph, inputs: T.Sequence[NTensor], outputs: T.Sequence[NTensor], op_type: str) -> T.Sequence[NTensor]

Ensure consistent rank between inputs and outputs with regard to spec.

  • May unsqueeze at 0 rank n time to align inputs

This is done at export time and not inference time because: - inference implementation may use 1 dim expansion from left to right like Tract or Tensorflow instead of PyTorch expansion which happen in opposite direction.

pick_axis 

pick_axis(input_node, rank: int) -> int

Enforce that axis, axes ect does contains only positive values.

pick_index_in_axis 

pick_index_in_axis(input_node, rank: int, index: int, check_is_positive: bool = True) -> int

Enforce that index in axis does contains only values within bounds.

Because in case of tract out of bound is not supported !