polygraphy.backend.tf.loader.SessionFromGraph Class Reference

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

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

Public Member Functions
def	__init__ (self, graph, config=None)
def	__call__ (self)

Public Attributes
	graph
	config

Constructor & Destructor Documentation

__init__()

def polygraphy.backend.tf.loader.SessionFromGraph.__init__	(		self,
			graph,
			config = None
	)

Functor that creates a TensorFlow session that can be used for inference.

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


    config (Callable() -> tf.ConfigProto):

Member Function Documentation

__call__()

def polygraphy.backend.tf.loader.SessionFromGraph.__call__

(

self

)

Creates a TensorFlow session.

Returns:
    tf.Session: The TensorFlow session.

Member Data Documentation

graph

polygraphy.backend.tf.loader.SessionFromGraph.graph

config

polygraphy.backend.tf.loader.SessionFromGraph.config

---

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

• backend/tf/loader.py