openvino.runtime.passes.LowLatency2¶
- class openvino.runtime.passes.LowLatency2¶
Bases:
openvino._pyopenvino.passes.ModelPass
,openvino._pyopenvino.passes.PassBase
openvino.runtime.passes.LowLatency2 transformation
- __init__(self: openvino._pyopenvino.passes.LowLatency2, use_const_initializer: bool = True) None ¶
Create LowLatency2 pass which is used for changing the structure of the model, which contains TensorIterator/Loop operations. The transformation finds all TensorIterator/Loop layers in the network, processes all back edges that describe a connection between Result and Parameter of the TensorIterator/Loop bodies, and inserts ReadValue and Assign layers at the input and output corresponding to this back edge.
- Parameters
use_const_initializer (bool) – Changes the type of the initializing subgraph for ReadValue operations. If “true”, then the transformation inserts Constant before ReadValue operation. If “false, then the transformation leaves existed initializing subgraph for ReadValue operation.
Methods
__delattr__
(name, /)Implement delattr(self, name).
__dir__
()Default dir() implementation.
__eq__
(value, /)Return self==value.
__format__
(format_spec, /)Default object formatter.
__ge__
(value, /)Return self>=value.
__getattribute__
(name, /)Return getattr(self, name).
__gt__
(value, /)Return self>value.
__hash__
()Return hash(self).
__init__
(self[, use_const_initializer])Create LowLatency2 pass which is used for changing the structure of the model, which contains TensorIterator/Loop operations.
This method is called when a class is subclassed.
__le__
(value, /)Return self<=value.
__lt__
(value, /)Return self<value.
__ne__
(value, /)Return self!=value.
__new__
(**kwargs)Helper for pickle.
__reduce_ex__
(protocol, /)Helper for pickle.
__repr__
(self)__setattr__
(name, value, /)Implement setattr(self, name, value).
Size of object in memory, in bytes.
__str__
()Return str(self).
Abstract classes can override this to customize issubclass().
get_name
(self)Get transformation name.
run_on_model
(self, model)run_on_model must be defined in inherited class.
set_name
(self, name)Set transformation name.
- __class__¶
alias of
pybind11_builtins.pybind11_type
- __delattr__(name, /)¶
Implement delattr(self, name).
- __dir__()¶
Default dir() implementation.
- __eq__(value, /)¶
Return self==value.
- __format__(format_spec, /)¶
Default object formatter.
- __ge__(value, /)¶
Return self>=value.
- __getattribute__(name, /)¶
Return getattr(self, name).
- __gt__(value, /)¶
Return self>value.
- __hash__()¶
Return hash(self).
- __init__(self: openvino._pyopenvino.passes.LowLatency2, use_const_initializer: bool = True) None ¶
Create LowLatency2 pass which is used for changing the structure of the model, which contains TensorIterator/Loop operations. The transformation finds all TensorIterator/Loop layers in the network, processes all back edges that describe a connection between Result and Parameter of the TensorIterator/Loop bodies, and inserts ReadValue and Assign layers at the input and output corresponding to this back edge.
- Parameters
use_const_initializer (bool) – Changes the type of the initializing subgraph for ReadValue operations. If “true”, then the transformation inserts Constant before ReadValue operation. If “false, then the transformation leaves existed initializing subgraph for ReadValue operation.
- __init_subclass__()¶
This method is called when a class is subclassed.
The default implementation does nothing. It may be overridden to extend subclasses.
- __le__(value, /)¶
Return self<=value.
- __lt__(value, /)¶
Return self<value.
- __ne__(value, /)¶
Return self!=value.
- __new__(**kwargs)¶
- __reduce__()¶
Helper for pickle.
- __reduce_ex__(protocol, /)¶
Helper for pickle.
- __repr__(self: openvino._pyopenvino.passes.LowLatency2) str ¶
- __setattr__(name, value, /)¶
Implement setattr(self, name, value).
- __sizeof__()¶
Size of object in memory, in bytes.
- __str__()¶
Return str(self).
- __subclasshook__()¶
Abstract classes can override this to customize issubclass().
This is invoked early on by abc.ABCMeta.__subclasscheck__(). It should return True, False or NotImplemented. If it returns NotImplemented, the normal algorithm is used. Otherwise, it overrides the normal algorithm (and the outcome is cached).
- get_name(self: openvino._pyopenvino.passes.PassBase) str ¶
Get transformation name.
- Returns
Transformation name.
- Return type
str
- run_on_model(self: openvino._pyopenvino.passes.ModelPass, model: openvino._pyopenvino.Model) bool ¶
run_on_model must be defined in inherited class. This method is used to work with Model directly.
- Parameters
model (openvino.runtime.Model) – openvino.runtime.Model to be transformed.
- Returns
True in case if Model was changed and False otherwise.
- Return type
bool
- set_name(self: openvino._pyopenvino.passes.PassBase, name: str) None ¶
Set transformation name.
- Parameters
name (str) – Transformation name.