polygraphy.backend.trt.loader.NetworkFromOnnxPath Class Reference

Inheritance diagram for polygraphy.backend.trt.loader.NetworkFromOnnxPath:

Collaboration diagram for polygraphy.backend.trt.loader.NetworkFromOnnxPath:

Public Member Functions
def	__init__ (self, path, explicit_precision=None)
def	__call__ (self)
def	__init__ (self, path, explicit_precision=None)

Public Attributes
	path
	explicit_precision
	explicit_batch

Constructor & Destructor Documentation

__init__() [1/2]

def polygraphy.backend.trt.loader.NetworkFromOnnxPath.__init__	(		self,
			path,
			explicit_precision = None
	)

Functor that parses an ONNX model to create a trt.INetworkDefinition.
This loader supports models with weights stored in an external location.

Args:
    path (str): The path from which to load the model.

Reimplemented from polygraphy.backend.trt.loader.BaseNetworkFromOnnx.

Here is the caller graph for this function:

__init__() [2/2]

def polygraphy.backend.trt.loader.NetworkFromOnnxPath.__init__	(		self,
			path,
			explicit_precision = None
	)

Functor that parses an ONNX model to create a trt.INetworkDefinition.
This loader supports models with weights stored in an external location.

Args:
    path (str): The path from which to load the model.

Reimplemented from polygraphy.backend.trt.loader.BaseNetworkFromOnnx.

Here is the call graph for this function:

Member Function Documentation

__call__()

def polygraphy.backend.trt.loader.NetworkFromOnnxPath.__call__

(

self

)

Parses an ONNX model from a file.

Returns:
    (trt.IBuilder, trt.INetworkDefinition, trt.OnnxParser):
A TensorRT network, as well as the builder used to create it, and the parser
used to populate it.

Reimplemented from polygraphy.backend.trt.loader.BaseNetworkFromOnnx.

Member Data Documentation

path

polygraphy.backend.trt.loader.NetworkFromOnnxPath.path

explicit_precision

polygraphy.backend.trt.loader.BaseNetworkFromOnnx.explicit_precision

inherited

explicit_batch

polygraphy.backend.trt.loader.BaseNetworkFromOnnx.explicit_batch

inherited

---

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

• backend/trt/loader.py