Operator Reference

HALCON Operator Reference / Deep Learning / Model

• HDevelop
• .NET
• Python
• C++
• C

ClassesClasses | | Operators

serialize_dl_modelT_serialize_dl_modelSerializeDlModelSerializeDlModelserialize_dl_model (Operator)

serialize_dl_modelT_serialize_dl_modelSerializeDlModelSerializeDlModelserialize_dl_model — Serialize a deep learning model.

Signature

serialize_dl_model( : : DLModelHandle : SerializedItemHandle)

Herror T_serialize_dl_model(const Htuple DLModelHandle, Htuple* SerializedItemHandle)

void SerializeDlModel(const HTuple& DLModelHandle, HTuple* SerializedItemHandle)

HSerializedItem HDlModel::SerializeDlModel() const

static void HOperatorSet.SerializeDlModel(HTuple DLModelHandle, out HTuple serializedItemHandle)

HSerializedItem HDlModel.SerializeDlModel()

def serialize_dl_model(dlmodel_handle: HHandle) -> HHandle

Description

serialize_dl_modelserialize_dl_modelSerializeDlModelSerializeDlModelserialize_dl_model serializes the deep learning model defined by the handle DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle. The serialized model is returned by the handle SerializedItemHandleSerializedItemHandleSerializedItemHandleserializedItemHandleserialized_item_handle and can be deserialized by deserialize_dl_modeldeserialize_dl_modelDeserializeDlModelDeserializeDlModeldeserialize_dl_model. See fwrite_serialized_itemfwrite_serialized_itemFwriteSerializedItemFwriteSerializedItemfwrite_serialized_item for an introduction of the basic principle of serialization.

The operator acts the same as write_dl_modelwrite_dl_modelWriteDlModelWriteDlModelwrite_dl_model except that the output is a serialized item instead of a file. For a detailed description please refer to the documentation of write_dl_modelwrite_dl_modelWriteDlModelWriteDlModelwrite_dl_model.

For further explanations to deep learning models in HALCON, see the chapter Deep Learning / Model.

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

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

Handle of the deep learning model.

SerializedItemHandleSerializedItemHandleSerializedItemHandleserializedItemHandleserialized_item_handle (output_control)  serialized_item → HSerializedItem, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Handle of the serialized item.

Result

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

Possible Predecessors

train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch, train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset

Possible Successors

train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch, train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset, fwrite_serialized_itemfwrite_serialized_itemFwriteSerializedItemFwriteSerializedItemfwrite_serialized_item, send_serialized_itemsend_serialized_itemSendSerializedItemSendSerializedItemsend_serialized_item

See also

deserialize_dl_modeldeserialize_dl_modelDeserializeDlModelDeserializeDlModeldeserialize_dl_model, apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelapply_dl_model, train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch, train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset

Module

Foundation. This operator uses dynamic licensing (see the 'Installation Guide'). Which of the following modules is required depends on the specific usage of the operator:
3D Metrology, OCR/OCV, Matching, Deep Learning Enhanced, Deep Learning Professional

---

ClassesClasses | | Operators