23.05
|
#include <Network.hpp>
Public Member Functions | |
~OptimizerOptionsOpaqueImpl ()=default | |
OptimizerOptionsOpaqueImpl () | |
OptimizerOptionsOpaqueImpl (bool reduceFp32ToFp16, bool debug, bool reduceFp32ToBf16, bool importEnabled, ModelOptions modelOptions={}, bool exportEnabled=false, bool debugToFile=false) | |
OptimizerOptionsOpaqueImpl (bool reduceFp32ToFp16, bool debug, bool reduceFp32ToBf16, ShapeInferenceMethod shapeInferenceMethod, bool importEnabled, ModelOptions modelOptions, bool exportEnabled, bool debugToFile, bool allowExpandedDims) | |
Public Attributes | |
bool | m_ReduceFp32ToFp16 = false |
Reduces all Fp32 operators in the model to Fp16 for faster processing. More... | |
bool | m_Debug = false |
Add debug data for easier troubleshooting. More... | |
bool | m_DebugToFile = false |
Pass debug data to separate output files for easier troubleshooting. More... | |
bool | m_ReduceFp32ToBf16 = false |
@Note This feature has been replaced by enabling Fast Math in compute library backend options. More... | |
ShapeInferenceMethod | m_shapeInferenceMethod = armnn::ShapeInferenceMethod::ValidateOnly |
Infer output size when not available. More... | |
bool | m_ImportEnabled = false |
Enable Import. More... | |
ModelOptions | m_ModelOptions |
Enable Model Options. More... | |
bool | m_ProfilingEnabled = false |
Enable profiling dump of the optimizer phase. More... | |
bool | m_ExportEnabled = false |
Enable Export. More... | |
bool | m_AllowExpandedDims = false |
When calculating tensor sizes, dimensions of size == 1 will be ignored. More... | |
Definition at line 296 of file Network.hpp.
|
default |
|
inlineexplicit |
|
inlineexplicit |
Definition at line 314 of file Network.hpp.
|
inlineexplicit |
bool m_AllowExpandedDims = false |
When calculating tensor sizes, dimensions of size == 1 will be ignored.
Definition at line 380 of file Network.hpp.
bool m_Debug = false |
Add debug data for easier troubleshooting.
Definition at line 355 of file Network.hpp.
bool m_DebugToFile = false |
Pass debug data to separate output files for easier troubleshooting.
Definition at line 358 of file Network.hpp.
bool m_ExportEnabled = false |
Enable Export.
Definition at line 377 of file Network.hpp.
bool m_ImportEnabled = false |
Enable Import.
Definition at line 368 of file Network.hpp.
ModelOptions m_ModelOptions |
Enable Model Options.
Definition at line 371 of file Network.hpp.
bool m_ProfilingEnabled = false |
Enable profiling dump of the optimizer phase.
Definition at line 374 of file Network.hpp.
bool m_ReduceFp32ToBf16 = false |
@Note This feature has been replaced by enabling Fast Math in compute library backend options.
This is currently a placeholder option
Definition at line 362 of file Network.hpp.
bool m_ReduceFp32ToFp16 = false |
Reduces all Fp32 operators in the model to Fp16 for faster processing.
@Note This feature works best if all operators of the model are in Fp32. ArmNN will add conversion layers between layers that weren't in Fp32 in the first place or if the operator is not supported in Fp16. The overhead of these conversions can lead to a slower overall performance if too many conversions are required.
Definition at line 352 of file Network.hpp.
ShapeInferenceMethod m_shapeInferenceMethod = armnn::ShapeInferenceMethod::ValidateOnly |
Infer output size when not available.
Definition at line 365 of file Network.hpp.