Skip to content

create_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruningT_create_dl_pruning🔗

Short description🔗

create_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruningT_create_dl_pruning — Create a pruning data handle.

Signature🔗

create_dl_pruning( dl_model DLModelHandle, string Mode, dict GenParam, out dl_pruning DLPruningHandle )void CreateDlPruning( const HTuple& DLModelHandle, const HTuple& Mode, const HTuple& GenParam, HTuple* DLPruningHandle )static void HOperatorSet.CreateDlPruning( HTuple DLModelHandle, HTuple mode, HTuple genParam, out HTuple DLPruningHandle )def create_dl_pruning( dlmodel_handle: HHandle, mode: str, gen_param: HHandle ) -> HHandle

Herror T_create_dl_pruning( const Htuple DLModelHandle, const Htuple Mode, const Htuple GenParam, Htuple* DLPruningHandle )

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)

public HDlPrune( HDlModel DLModelHandle, string mode, HDict genParam )

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::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)

HDlPrune HDlModel.CreateDlPruning( string mode, HDict genParam )

void HDlPrune.CreateDlPruning( HDlModel DLModelHandle, string mode, HDict genParam )

Description🔗

The operator create_dl_pruningCreateDlPruning creates a handle DLPruningHandleDLPruningHandledlpruning_handle. This handle is used to pass information when pruning a deep learning model.

Modemodemode specifies the pruning method. The mode implies what will be removed and also which scores are needed. Currently only the following 'mode'"mode" is implemented:

  • '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.

GenParamgenParamgen_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🔗

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🔗

DLModelHandleDLModelHandledlmodel_handle (input_control) dl_model → (handle)HTuple (HHandle)HDlModel, HTuple (IntPtr)HHandleHtuple (handle)

Handle of a deep learning model.

Modemodemode (input_control) string → (string)HTuple (HString)HTuple (string)strHtuple (char*)

Pruning method.

Default: 'oracle'"oracle"
List of values: 'oracle'"oracle"

GenParamgenParamgen_param (input_control) dict → (handle)HTuple (HHandle)HDict, HTuple (IntPtr)HHandleHtuple (handle)

Dictionary with generic parameters.

Default: [][]

DLPruningHandleDLPruningHandledlpruning_handle (output_control) dl_pruning → (handle)HTuple (HHandle)HDlPrune, HTuple (IntPtr)HHandleHtuple (handle)

Pruning data handle.

Combinations with other operators🔗

Combinations

Possible predecessors

read_dl_modelReadDlModel

Possible successors

get_dl_pruning_paramGetDlPruningParam, set_dl_model_paramSetDlModelParam

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 Professional