Skip to content

load_dl_model_weightsLoadDlModelWeightsLoadDlModelWeightsload_dl_model_weightsT_load_dl_model_weights🔗

Short description🔗

load_dl_model_weightsLoadDlModelWeightsLoadDlModelWeightsload_dl_model_weightsT_load_dl_model_weights — Load the weights of a source model into a target model.

Signature🔗

load_dl_model_weights( dl_model DLModelHandleSource, dl_model DLModelHandleTarget, out integer ChangesByLayer )void LoadDlModelWeights( const HTuple& DLModelHandleSource, const HTuple& DLModelHandleTarget, HTuple* ChangesByLayer )static void HOperatorSet.LoadDlModelWeights( HTuple DLModelHandleSource, HTuple DLModelHandleTarget, out HTuple changesByLayer )def load_dl_model_weights( dlmodel_handle_source: HHandle, dlmodel_handle_target: HHandle ) -> Sequence[int]

def load_dl_model_weights_s( dlmodel_handle_source: HHandle, dlmodel_handle_target: HHandle ) -> intHerror T_load_dl_model_weights( const Htuple DLModelHandleSource, const Htuple DLModelHandleTarget, Htuple* ChangesByLayer )

HTuple HDlModel::LoadDlModelWeights( const HDlModel& DLModelHandleTarget ) const

HTuple HDlModel.LoadDlModelWeights( HDlModel DLModelHandleTarget )

Description🔗

The operator load_dl_model_weightsLoadDlModelWeights loads weights of a source model DLModelHandleSourceDLModelHandleSourcedlmodel_handle_source into a target model DLModelHandleTargetDLModelHandleTargetdlmodel_handle_target. Thereby applies for every layer in the target model: Its weights are only changed if there is a layer in the source model having the same name and the same weight-shape. Note that DLModelHandleSourceDLModelHandleSourcedlmodel_handle_source must be different from DLModelHandleTargetDLModelHandleTargetdlmodel_handle_target, i.e., you cannot use the same model handle as source and target.

ChangesByLayerchangesByLayerchanges_by_layer is a tuple indicating for every target layer how many weights changed. Its entries are sorted by ascending layer IDs. The layer IDs can be queried via the operator get_dl_model_paramGetDlModelParam with the parameter 'summary'"summary".

Note, that 'weights' means all weights and biases for all layers which can have such values (e.g., convolutional layer, batch normalization layer, etc.).

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.

Parameters🔗

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

Handle of the source deep learning model.

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

Handle of the target deep learning model.

ChangesByLayerchangesByLayerchanges_by_layer (output_control) integer(-array) → (integer)HTuple (Hlong)HTuple (int / long)Sequence[int]Htuple (Hlong)

Indicates for every target layer how many weights changed.

Result🔗

If the parameters are valid, the operator load_dl_model_weightsLoadDlModelWeights returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.

Module🔗

Deep Learning Professional