gen_dl_pruned_model — Prune a deep learning model.
gen_dl_pruned_model( : : DLModelHandleToPrune, DLPruningHandle : DLModelHandlePruned)
The operator gen_dl_pruned_model copies the input model
DLModelHandleToPrune and returns the pruned copy in
DLModelHandlePruned.
Note that gen_dl_pruned_model supports only deep learning
models of 'type'='classification'.
The parameter DLPruningHandle provides the necessary information
as e.g., the selected pruning mode, the percentage or the kernel scores.
See create_dl_pruning for further information about
implemented pruning modes.
Behavior in special cases:
In case the set amount of pruning 'percentage' is too small to
result in any removals, the returned model DLModelHandlePruned
is simply a copy of the input model DLModelHandleToPrune.
In case the model could not be pruned successfully, an empty handle is returned.
DLModelHandleToPrune (input_control) dl_model → (handle)
Input model.
DLPruningHandle (input_control) dl_pruning → (handle)
Pruning data handle.
DLModelHandlePruned (output_control) dl_model → (handle)
Pruned model.
add_dl_pruning_batch,
set_dl_pruning_param
Deep Learning Training