Operator Reference

HALCON Operator Reference / Deep Learning / Model

• HDevelop
• .NET
• Python
• C++
• C

ClassesClasses | | Operators

gen_dl_pruned_modelT_gen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model (Operator)

gen_dl_pruned_modelT_gen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model — Prune a deep learning model.

Signature

gen_dl_pruned_model( : : DLModelHandleToPrune, DLPruningHandle : DLModelHandlePruned)

Herror T_gen_dl_pruned_model(const Htuple DLModelHandleToPrune, const Htuple DLPruningHandle, Htuple* DLModelHandlePruned)

void GenDlPrunedModel(const HTuple& DLModelHandleToPrune, const HTuple& DLPruningHandle, HTuple* DLModelHandlePruned)

HDlModel HDlModel::GenDlPrunedModel(const HDlPrune& DLPruningHandle) const

static void HOperatorSet.GenDlPrunedModel(HTuple DLModelHandleToPrune, HTuple DLPruningHandle, out HTuple DLModelHandlePruned)

HDlModel HDlModel.GenDlPrunedModel(HDlPrune DLPruningHandle)

def gen_dl_pruned_model(dlmodel_handle_to_prune: HHandle, dlpruning_handle: HHandle) -> HHandle

Description

The operator gen_dl_pruned_modelgen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model copies the input model DLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune and returns the pruned copy in DLModelHandlePrunedDLModelHandlePrunedDLModelHandlePrunedDLModelHandlePruneddlmodel_handle_pruned. Note that gen_dl_pruned_modelgen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model supports only deep learning models of 'type'"type""type""type""type"='classification'"classification""classification""classification""classification".

The parameter DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle provides the necessary information as e.g., the selected pruning mode, the percentage or the kernel scores. See create_dl_pruningcreate_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruning for further information about implemented pruning modes.

Behavior in special cases:

• In case the set amount of pruning 'percentage'"percentage""percentage""percentage""percentage" is too small to result in any removals, the returned model DLModelHandlePrunedDLModelHandlePrunedDLModelHandlePrunedDLModelHandlePruneddlmodel_handle_pruned is simply a copy of the input model DLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune.

• In case the model could not be pruned successfully, an empty handle is returned.

Execution Information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).
• Multithreading scope: global (may be called from any thread).
• Processed without parallelization.

Parameters

DLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune (input_control)  dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Input model.

DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle (input_control)  dl_pruning → HDlPrune, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Pruning data handle.

DLModelHandlePrunedDLModelHandlePrunedDLModelHandlePrunedDLModelHandlePruneddlmodel_handle_pruned (output_control)  dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Pruned model.

Possible Predecessors

add_dl_pruning_batchadd_dl_pruning_batchAddDlPruningBatchAddDlPruningBatchadd_dl_pruning_batch, set_dl_pruning_paramset_dl_pruning_paramSetDlPruningParamSetDlPruningParamset_dl_pruning_param

Module

Deep Learning Professional

---

ClassesClasses | | Operators