polygraphy.backend.trt.loader.NetworkFromOnnxBytes Class Reference

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

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

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

Public Attributes
	explicit_precision
	explicit_batch

Private Attributes
	_model_bytes

Constructor & Destructor Documentation

__init__()

def polygraphy.backend.trt.loader.NetworkFromOnnxBytes.__init__	(		self,
			model_bytes,
			explicit_precision = None
	)

Functor that parses an ONNX model to create a trt.INetworkDefinition.

Args:
    model_bytes (Callable() -> bytes): A loader that can supply a serialized ONNX model.

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

Member Function Documentation

__call__()

def polygraphy.backend.trt.loader.NetworkFromOnnxBytes.__call__

(

self

)

Parses an ONNX model.

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

_model_bytes

polygraphy.backend.trt.loader.NetworkFromOnnxBytes._model_bytes

private

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