finn.custom_op.base (module)¶
-
class
finn.custom_op.base.CustomOp(onnx_node)¶ Bases:
abc.ABCCustomOp class all custom op nodes are based on. Contains different functions every custom node should have. Some as abstract methods, these have to be filled when writing a new custom op node.
-
abstract
execute_node(context, graph)¶ Execute this CustomOp instance, given the execution context and ONNX graph.
-
get_nodeattr(name)¶ Get a node attribute by name. Data is stored inside the ONNX node’s AttributeProto container. Attribute must be part of get_nodeattr_types. Default value is returned if attribute is not set.
-
abstract
get_nodeattr_types()¶ Returns a dict of permitted attributes for node, where: returned_dict[attribute_name] = (dtype, require, default_value) - dtype indicates which member of the ONNX AttributeProto will be utilized - require indicates whether this attribute is required - default_val indicates the default value that will be used if the attribute is not set
-
abstract
infer_node_datatype(model)¶ Set the DataType annotations corresponding to the outputs of this node.
-
abstract
make_shape_compatible_op(model)¶ Returns a standard ONNX op which is compatible with this CustomOp for performing shape inference.
-
set_nodeattr(name, value)¶ Set a node attribute by name. Data is stored inside the ONNX node’s AttributeProto container. Attribute must be part of get_nodeattr_types.
-
abstract
verify_node()¶ Verifies that all attributes the node needs are there and that particular attributes are set correctly. Also checks if the number of inputs is equal to the expected number.
-
abstract