polygraphy.backend.tf.loader.OptimizeGraph Class Reference

Inheritance diagram for polygraphy.backend.tf.loader.OptimizeGraph:

Collaboration diagram for polygraphy.backend.tf.loader.OptimizeGraph:

Public Member Functions
def	__init__ (self, graph)
def	constfold (self, graphdef, output_names)
def	__call__ (self)

Private Attributes
	_graph

Constructor & Destructor Documentation

__init__()

def polygraphy.backend.tf.loader.OptimizeGraph.__init__	(		self,
			graph
	)

Functor that freezes a TensorFlow graph, and folds constants.

Args:
    graph (Callable() -> Tuple[tf.Graph, Sequence[str]]):
    A callable that can supply a tuple containing a TensorFlow graph and output names.

Member Function Documentation

constfold()

def polygraphy.backend.tf.loader.OptimizeGraph.constfold	(		self,
			graphdef,
			output_names
	)

Here is the caller graph for this function:

__call__()

def polygraphy.backend.tf.loader.OptimizeGraph.__call__

(

self

)

Freezes a TensorFlow graph, and folds constants.

Returns:
    Tuple[tf.Graph, Sequence[str]]: The TensorFlow graph, and the names of its outputs.

Here is the call graph for this function:

Member Data Documentation

_graph

polygraphy.backend.tf.loader.OptimizeGraph._graph

private

---

The documentation for this class was generated from the following file:

• backend/tf/loader.py