HALCON Website / HALCON Operator-Referenz / Deep Learning / Framework
KlassenKlassen | | Operatoren

get_dl_model_layer_paramT_get_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param (Operator)

Name

get_dl_model_layer_paramT_get_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param — Auslesen der Parameterwerte des angegebenen Layers.

Signatur

get_dl_model_layer_param( : : DLModelHandle, LayerName, ParamName : ParamValue)

Herror T_get_dl_model_layer_param(const Htuple DLModelHandle, const Htuple LayerName, const Htuple ParamName, Htuple* ParamValue)

void GetDlModelLayerParam(const HTuple& DLModelHandle, const HTuple& LayerName, const HTuple& ParamName, HTuple* ParamValue)

static HTuple HDlLayer::GetDlModelLayerParam(const HDlModel& DLModelHandle, const HString& LayerName, const HString& ParamName)

static HTuple HDlLayer::GetDlModelLayerParam(const HDlModel& DLModelHandle, const char* LayerName, const char* ParamName)

static HTuple HDlLayer::GetDlModelLayerParam(const HDlModel& DLModelHandle, const wchar_t* LayerName, const wchar_t* ParamName)   (Nur Windows)

static void HOperatorSet.GetDlModelLayerParam(HTuple DLModelHandle, HTuple layerName, HTuple paramName, out HTuple paramValue)

static HTuple HDlLayer.GetDlModelLayerParam(HDlModel DLModelHandle, string layerName, string paramName)

def get_dl_model_layer_param(dlmodel_handle: HHandle, layer_name: str, param_name: str) -> Sequence[Union[str, float, int]]

def get_dl_model_layer_param_s(dlmodel_handle: HHandle, layer_name: str, param_name: str) -> Union[str, float, int]

Beschreibung

Der Operator get_dl_model_layer_paramget_dl_model_layer_paramGetDlModelLayerParamGetDlModelLayerParamGetDlModelLayerParamget_dl_model_layer_param gibt für den angegebenen Layer den Wert des Parameters ParamNameParamNameParamNameParamNameparamNameparam_name in ParamValueParamValueParamValueParamValueparamValueparam_value zurück. Der Layername LayerNameLayerNameLayerNameLayerNamelayerNamelayer_name bezieht sich auf den im Model DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle zugeordneten Namen. Die Layernamen können über die Option 'layer_names'"layer_names""layer_names""layer_names""layer_names""layer_names" oder 'summary'"summary""summary""summary""summary""summary" mit get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param ausgelesen werden.

Welche generischen und Layer-spezifischen Parameter abgefragt werden können wird in den spezifischen Operatorreferenzen (create_dl_layer_*) beschrieben.

Ausführungsinformationen

Parameter

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

Handle des Deep Learning-Modells.

LayerNameLayerNameLayerNameLayerNamelayerNamelayer_name (input_control)  string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)

Name des Ausgabelayers.

ParamNameParamNameParamNameParamNameparamNameparam_name (input_control)  string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)

Name des abgefragten Parameters.

Defaultwert: 'type' "type" "type" "type" "type" "type"

Werteliste: 'bias_filler'"bias_filler""bias_filler""bias_filler""bias_filler""bias_filler", 'bias_filler_const_val'"bias_filler_const_val""bias_filler_const_val""bias_filler_const_val""bias_filler_const_val""bias_filler_const_val", 'bias_filler_variance_norm'"bias_filler_variance_norm""bias_filler_variance_norm""bias_filler_variance_norm""bias_filler_variance_norm""bias_filler_variance_norm", 'bias_term'"bias_term""bias_term""bias_term""bias_term""bias_term", 'input_layer'"input_layer""input_layer""input_layer""input_layer""input_layer", 'is_inference_output'"is_inference_output""is_inference_output""is_inference_output""is_inference_output""is_inference_output", 'leaky_relu_alpha'"leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha""leaky_relu_alpha", 'learning_rate_multiplier'"learning_rate_multiplier""learning_rate_multiplier""learning_rate_multiplier""learning_rate_multiplier""learning_rate_multiplier", 'learning_rate_multiplier_bias'"learning_rate_multiplier_bias""learning_rate_multiplier_bias""learning_rate_multiplier_bias""learning_rate_multiplier_bias""learning_rate_multiplier_bias", 'name'"name""name""name""name""name", 'num_trainable_params'"num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params""num_trainable_params", 'output_layer'"output_layer""output_layer""output_layer""output_layer""output_layer", 'shape'"shape""shape""shape""shape""shape", 'type'"type""type""type""type""type", 'upper_bound'"upper_bound""upper_bound""upper_bound""upper_bound""upper_bound", 'weight_filler'"weight_filler""weight_filler""weight_filler""weight_filler""weight_filler", 'weight_filler_const_val'"weight_filler_const_val""weight_filler_const_val""weight_filler_const_val""weight_filler_const_val""weight_filler_const_val", 'weight_filler_variance_norm'"weight_filler_variance_norm""weight_filler_variance_norm""weight_filler_variance_norm""weight_filler_variance_norm""weight_filler_variance_norm"

Restriktion: length(ParamName) > 0

ParamValueParamValueParamValueParamValueparamValueparam_value (output_control)  tuple(-array) → HTupleSequence[Union[str, float, int]]HTupleHtuple (string / real / integer) (string / double / int / long) (HString / double / Hlong) (char* / double / Hlong)

Wert des abgefragten Parameters.

Siehe auch

get_dl_model_paramget_dl_model_paramGetDlModelParamGetDlModelParamGetDlModelParamget_dl_model_param, set_dl_model_layer_paramset_dl_model_layer_paramSetDlModelLayerParamSetDlModelLayerParamSetDlModelLayerParamset_dl_model_layer_param

Modul

Foundation. Dieser Operator verwendet dynamische Lizensierung (siehe ``Installation Guide''). Welches der folgenden Module benötigt wird hängt von der Anwendung des Operators ab:
3D Metrology, OCR/OCV, Deep Learning Training

KlassenKlassen | | Operatoren
HALCON Operator-Referenz 22.11.4.0 Copyright © 1996-2025 MVTec Software GmbH
Follow us on