module `training._base_onnx_function`#

Short summary#

module onnxcustom.training._base_onnx_function

Classes#

class	truncated documentation
`BaseLearningOnnx`	Class handling ONNX function to manipulate OrtValue. Base class for `BaseLearningRate` and `BaseLearningLoss`. …

Static Methods#

staticmethod	truncated documentation
`_bio_cache`
`_bio_do_bind_in`
`_bio_do_bind_out`
`_bio_ptr`
`_cache_in_clear`

Methods#

method	truncated documentation
`__getstate__`	Overwrites getstate to get rid of InferenceSession.
`__init__`
`__repr__`	Usual
`__repr_extended__`
`__setstate__`	Overwrites getstate to get rid of InferenceSession.
`_bind_input_ortvalue`	Binds C_OrtValue to the structure used by InferenceSession to run inference.
`_bind_output_ortvalue`	Binds C_OrtValue to the structure used by InferenceSession to run inference.
`build_onnx_function`	This class computes a function represented as an ONNX graph. This method builds it. This function creates …
`clear_binding_inputs`	Clears binding and empty cache.

Documentation#

Helper for onnxruntime-training.

source on GitHub

class onnxcustom.training._base_onnx_function.BaseLearningOnnx#

Bases: BaseOnnxClass

Class handling ONNX function to manipulate OrtValue. Base class for BaseLearningRate and BaseLearningLoss.

source on GitHub

__getstate__()#

Overwrites getstate to get rid of InferenceSession.

source on GitHub

__init__()#

__repr__()#

Usual

source on GitHub

__repr_extended__()#

__setstate__(state)#

Overwrites getstate to get rid of InferenceSession.

source on GitHub

_bind_input_ortvalue(name, bind, c_ortvalue, device, cache=False)#

Binds C_OrtValue to the structure used by InferenceSession to run inference.

Parameters:

name – str
bind – python structure
c_ortvalue – C structure for OrtValue (C_OrtValue), it can be also a numpy array
device – device
cache – avoids binding again if the data pointer did not change, only works when c_ortvalue is of C_OrtValue, the cache is equivalent to a dictionary { id(bind), name: c_ort_value.data_ptr() }.

source on GitHub

_bind_output_ortvalue(name, bind, c_ortvalue, cache=False)#

Binds C_OrtValue to the structure used by InferenceSession to run inference.

Parameters:

name – str
bind – python structure
c_ortvalue – C structure for OrtValue (C_OrtValue)
cache – avoids binding again if the data pointer did not change, only works when c_ortvalue is of C_OrtValue, the cache is equivalent to a dictionary { id(bind), name: c_ort_value.data_ptr() }.

This method can be used for inplace computation.

source on GitHub

static _bio_cache(cache, name, bind, c_ortvalue, ptr2)#

static _bio_do_bind_in(name, bind, c_ortvalue)#

static _bio_do_bind_out(name, bind, c_ortvalue)#

static _bio_ptr(c)#

static _cache_in_clear(cache, name, bind)#

build_onnx_function(opset, device, *args)#

This class computes a function represented as an ONNX graph. This method builds it. This function creates InferenceSession which do that.

Parameters:

opset – opset to use
device – C_OrtDevice
args – additional arguments

source on GitHub

clear_binding_inputs(name, bind, cache=False)#

Clears binding and empty cache.

source on GitHub

module training._base_onnx_function#

Short summary#

Classes#

Static Methods#

Methods#

Documentation#

module `training._base_onnx_function`#