get_dl_pruning_paramT_get_dl_pruning_paramGetDlPruningParamGetDlPruningParamget_dl_pruning_param (Operator)

Name

get_dl_pruning_paramT_get_dl_pruning_paramGetDlPruningParamGetDlPruningParamget_dl_pruning_param — Get information from a pruning data handle.

Signature

get_dl_pruning_param( : : DLPruningHandle, GenParamName : GenParamValue)

Description

get_dl_pruning_paramget_dl_pruning_paramGetDlPruningParamGetDlPruningParamGetDlPruningParamget_dl_pruning_param returns the parameter and pruning values GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value of GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name from the pruning data handle DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle.

The values of following parameters GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name can be retrieved:

'mode'"mode""mode""mode""mode""mode":

Specifies the pruning method See create_dl_pruningcreate_dl_pruningCreateDlPruningCreateDlPruningCreateDlPruningcreate_dl_pruning for further information.

Default: 'oracle'"oracle""oracle""oracle""oracle""oracle"

'percentage'"percentage""percentage""percentage""percentage""percentage":

Determines how much will be removed in percents. E.g., in case of 'mode'"mode""mode""mode""mode""mode"='oracle'"oracle""oracle""oracle""oracle""oracle" it specifies the relative amount of possibly removable kernels to be removed, whereby only removable kernels are considered.

Default: 10

Additionally, for 'mode'"mode""mode""mode""mode""mode"='oracle'"oracle""oracle""oracle""oracle""oracle", the following pruning values can be retrieved using GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name:

'prunable_conv_num'"prunable_conv_num""prunable_conv_num""prunable_conv_num""prunable_conv_num""prunable_conv_num":: Number of prunable convolutional layers in the network. Whether a layer is prunable depends on the specifications of the layer itself as well as the network architecture.
'prunable_conv_layer_name'"prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name":: Names of the prunable convolutional layers in the network.
'prunable_kernel_num'"prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num":: Number of prunable convolution kernels in the network. It considers that a pruned convolution has to retain at least 1 convolution kernel.
'pruned_kernel_num'"pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num":: Number of pruned convolution kernels in the network after a call of gen_dl_pruned_modelgen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model.
'pruned_percentage'"pruned_percentage""pruned_percentage""pruned_percentage""pruned_percentage""pruned_percentage":: Actual percentage of pruned convolution kernels in the network after a call of gen_dl_pruned_modelgen_dl_pruned_modelGenDlPrunedModelGenDlPrunedModelGenDlPrunedModelgen_dl_pruned_model: the ratio 'pruned_kernel_num'"pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num" versus 'prunable_kernel_num'"prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num".

The following table gives an overview, which parameters and values can be set using set_dl_pruning_paramset_dl_pruning_paramSetDlPruningParamSetDlPruningParamSetDlPruningParamset_dl_pruning_param and which ones can be retrieved using get_dl_pruning_paramget_dl_pruning_paramGetDlPruningParamGetDlPruningParamGetDlPruningParamget_dl_pruning_param.

Parameters	set	get
'mode'"mode""mode""mode""mode""mode"
'percentage'"percentage""percentage""percentage""percentage""percentage"
'prunable_conv_num'"prunable_conv_num""prunable_conv_num""prunable_conv_num""prunable_conv_num""prunable_conv_num"
'prunable_conv_layer_name'"prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name"
'prunable_kernel_num'"prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num"
'pruned_kernel_num'"pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num"
'pruned_percentage'"pruned_percentage""pruned_percentage""pruned_percentage""pruned_percentage""pruned_percentage"

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

DLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandleDLPruningHandledlpruning_handle (input_control) dl_pruning → (handle)

Pruning data handle.

GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (input_control) attribute.name → (string)

Name of the generic parameter.

Default: 'percentage' "percentage" "percentage" "percentage" "percentage" "percentage"

List of values: 'mode'"mode""mode""mode""mode""mode", 'percentage'"percentage""percentage""percentage""percentage""percentage", 'prunable_conv_layer_name'"prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name""prunable_conv_layer_name", 'prunable_conv_num'"prunable_conv_num""prunable_conv_num""prunable_conv_num""prunable_conv_num""prunable_conv_num", 'prunable_kernel_num'"prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num""prunable_kernel_num", 'pruned_kernel_num'"pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num""pruned_kernel_num", 'pruned_percentage'"pruned_percentage""pruned_percentage""pruned_percentage""pruned_percentage""pruned_percentage"

GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (output_control) attribute.name(-array) → (integer / string / real)

Value of the generic parameter.

Possible Predecessors

create_dl_pruningcreate_dl_pruningCreateDlPruningCreateDlPruningCreateDlPruningcreate_dl_pruning, set_dl_pruning_paramset_dl_pruning_paramSetDlPruningParamSetDlPruningParamSetDlPruningParamset_dl_pruning_param

Module

Deep Learning Training

Operators