add_dl_pruning_batchT_add_dl_pruning_batchAddDlPruningBatchAddDlPruningBatchadd_dl_pruning_batch (Operator)
Name
add_dl_pruning_batchT_add_dl_pruning_batchAddDlPruningBatchAddDlPruningBatchadd_dl_pruning_batch — Calculate scores to prune a deep learning model.
Signature
Description
add_dl_pruning_batchadd_dl_pruning_batchAddDlPruningBatchAddDlPruningBatchadd_dl_pruning_batch calculates pruning scores for the deep
learning model DLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune.
More precisely, the scores are calculated on the images given in
DLSampleBatchDLSampleBatchDLSampleBatchDLSampleBatchdlsample_batch and internally accumulated by each call of
add_dl_pruning_batchadd_dl_pruning_batchAddDlPruningBatchAddDlPruningBatchadd_dl_pruning_batch in the pruning data handle
DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle.
The parameter DLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune specifies the deep learning
model to use.
Note that add_dl_pruning_batchadd_dl_pruning_batchAddDlPruningBatchAddDlPruningBatchadd_dl_pruning_batch supports only deep learning
models of type 'classification'"classification""classification""classification""classification".
The parameter DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle specifies the pruning data handle,
which is used to pass information as e.g., the accumulated scores or the
pruning mode.
See create_dl_pruningcreate_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruning for further information about implemented
pruning modes.
The parameter DLSampleBatchDLSampleBatchDLSampleBatchDLSampleBatchdlsample_batch specifies the batch with input images
based on which the scores are calculated.
Note that the number of images in the tuple DLSampleBatchDLSampleBatchDLSampleBatchDLSampleBatchdlsample_batch needs to
be equal to the value set for the model parameter 'batch_size'"batch_size""batch_size""batch_size""batch_size".
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.
Parameters
DLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPruneDLModelHandleToPrunedlmodel_handle_to_prune (input_control) dl_model → HDlModel, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Handle of a deep learning model to prune.
DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle (input_control) dl_pruning → HDlPrune, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Pruning data handle.
DLSampleBatchDLSampleBatchDLSampleBatchDLSampleBatchdlsample_batch (input_control) dict-array → HDict, HTupleSequence[HHandle]HTupleHtuple (handle) (IntPtr) (HHandle) (handle)
Tuple of dictionaries with input images.
Possible Predecessors
read_dl_modelread_dl_modelReadDlModelReadDlModelread_dl_model,
create_dl_pruningcreate_dl_pruningCreateDlPruningCreateDlPruningcreate_dl_pruning,
set_dl_pruning_paramset_dl_pruning_paramSetDlPruningParamSetDlPruningParamset_dl_pruning_param
Possible Successors
get_dl_pruning_paramget_dl_pruning_paramGetDlPruningParamGetDlPruningParamget_dl_pruning_param,
gen_dl_pruned_modelgen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model
Module
Deep Learning Professional