Inheritance diagram for polygraphy.backend.onnx.loader.OnnxFromTfGraph:

Collaboration diagram for polygraphy.backend.onnx.loader.OnnxFromTfGraph:

Public Member Functions
def	__init__ (self, graph, opset=None, optimize=None, fold_constant=None)

def	__call__ (self)

Public Attributes
	opset

	fold_constant

	optimize

Private Attributes
	_graph

Constructor & Destructor Documentation

◆ init()

def polygraphy.backend.onnx.loader.OnnxFromTfGraph.__init__	(	self,
		graph,
		opset = `None`,
		optimize = `None`,
		fold_constant = `None`
	)

Functor that loads a TensorFlow graph and converts it to ONNX using the tf2onnx converter.

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


    opset (int): The ONNX opset to use during conversion.
    optimize (bool): Whether to use tf2onnx's graph optimization pass.
    fold_constant (bool):
    Whether to fold constants in the TensorFlow Graph.
    Requires that ``optimize`` is also enabled.
    Defaults to True.

Member Function Documentation

◆ call()

def polygraphy.backend.onnx.loader.OnnxFromTfGraph.__call__ ( self )

Converts a TensorFlow model into ONNX.

Returns:
    onnx.ModelProto: The ONNX model.

Member Data Documentation

◆ _graph

polygraphy.backend.onnx.loader.OnnxFromTfGraph._graph

private

◆ opset

polygraphy.backend.onnx.loader.OnnxFromTfGraph.opset

◆ fold_constant

polygraphy.backend.onnx.loader.OnnxFromTfGraph.fold_constant

◆ optimize

polygraphy.backend.onnx.loader.OnnxFromTfGraph.optimize

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

backend/onnx/loader.py

Public Member Functions

Public Attributes

Private Attributes