create_dl_pruningT_create_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruning (Operator)
Name
create_dl_pruningT_create_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruning — Create a pruning data handle.
Signature
void CreateDlPruning(const HTuple& DLModelHandle, const HTuple& Mode, const HTuple& GenParam, HTuple* DLPruningHandle)
HDlPrune HDlModel::CreateDlPruning(const HString& Mode, const HDict& GenParam) const
HDlPrune HDlModel::CreateDlPruning(const char* Mode, const HDict& GenParam) const
HDlPrune HDlModel::CreateDlPruning(const wchar_t* Mode, const HDict& GenParam) const
(Windows only)
void HDlPrune::HDlPrune(const HDlModel& DLModelHandle, const HString& Mode, const HDict& GenParam)
void HDlPrune::HDlPrune(const HDlModel& DLModelHandle, const char* Mode, const HDict& GenParam)
void HDlPrune::HDlPrune(const HDlModel& DLModelHandle, const wchar_t* Mode, const HDict& GenParam)
(Windows only)
void HDlPrune::CreateDlPruning(const HDlModel& DLModelHandle, const HString& Mode, const HDict& GenParam)
void HDlPrune::CreateDlPruning(const HDlModel& DLModelHandle, const char* Mode, const HDict& GenParam)
void HDlPrune::CreateDlPruning(const HDlModel& DLModelHandle, const wchar_t* Mode, const HDict& GenParam)
(Windows only)
Description
The operator create_dl_pruningcreate_dl_pruningCreateDlPruningCreateDlPruningCreateDlPruningcreate_dl_pruning creates a handle
DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle.
This handle is used to pass information when pruning a deep learning model.
ModeModeModeModemodemode specifies the pruning method.
The mode implies what will be removed and also which scores are needed.
Currently only the following 'mode'"mode""mode""mode""mode""mode" is implemented:
- 'oracle'"oracle""oracle""oracle""oracle""oracle":
Kernels of convolution layers are removed.
In order to do so, a score is calculated for every (potentially removable)
kernel, indicating its importance within the given network for the images
used. See the given reference for details.
GenParamGenParamGenParamGenParamgenParamgen_param is a dictionary for setting generic parameters.
Currently no generic parameters are supported.
For an explanation of the concept of deep learning
see the introduction of chapter Deep Learning.
Execution Information
- Multithreading type: reentrant (runs in parallel with non-exclusive operators).
- Multithreading scope: global (may be called from any thread).
- Processed without parallelization.
This operator returns a handle. Note that the state of an instance of this handle type may be changed by specific operators even though the handle is used as an input parameter by those operators.
Parameters
DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle (input_control) dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of a deep learning model.
ModeModeModeModemodemode (input_control) string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)
Pruning method.
Default value:
'oracle'
"oracle"
"oracle"
"oracle"
"oracle"
"oracle"
List of values: 'oracle'"oracle""oracle""oracle""oracle""oracle"
GenParamGenParamGenParamGenParamgenParamgen_param (input_control) dict → HDict, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Dictionary with generic parameters.
Default value: []
DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle (output_control) dl_pruning → HDlPrune, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Pruning data handle.
Possible Predecessors
read_dl_modelread_dl_modelReadDlModelReadDlModelReadDlModelread_dl_model
Possible Successors
get_dl_pruning_paramget_dl_pruning_paramGetDlPruningParamGetDlPruningParamGetDlPruningParamget_dl_pruning_param,
set_dl_model_paramset_dl_model_paramSetDlModelParamSetDlModelParamSetDlModelParamset_dl_model_param
References
Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, Jan Kautz
"Pruning Convolutional Neural Networks for Resource Efficient Inference",
ICLR 2017, 5th International Conference on Learning Representations, Toulon,
France.
Module
Deep Learning Training