serialize_dl_modelT_serialize_dl_modelSerializeDlModelSerializeDlModelserialize_dl_model (算子)

名称

serialize_dl_modelT_serialize_dl_modelSerializeDlModelSerializeDlModelserialize_dl_model — 序列化深度学习模型。

签名

serialize_dl_model( : : DLModelHandle : SerializedItemHandle)

描述

serialize_dl_modelserialize_dl_modelSerializeDlModelSerializeDlModelSerializeDlModelserialize_dl_model serializes the deep learning model defined by the handle DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle. The serialized model is returned by the handle SerializedItemHandleSerializedItemHandleSerializedItemHandleSerializedItemHandleserializedItemHandleserialized_item_handle and can be deserialized by deserialize_dl_modeldeserialize_dl_modelDeserializeDlModelDeserializeDlModelDeserializeDlModeldeserialize_dl_model. See fwrite_serialized_itemfwrite_serialized_itemFwriteSerializedItemFwriteSerializedItemFwriteSerializedItemfwrite_serialized_item for an introduction of the basic principle of serialization.

The operator acts the same as write_dl_modelwrite_dl_modelWriteDlModelWriteDlModelWriteDlModelwrite_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_modelWriteDlModelWriteDlModelWriteDlModelwrite_dl_model.

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

执行信息

多线程类型：可重入（与非独占算子并行运行）。
多线程作用域：全局（可从任何线程调用）。
未采用并行化处理。

参数

DLModelHandleDLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle (输入控制) dl_model → (handle)

Handle of the deep learning model.

SerializedItemHandleSerializedItemHandleSerializedItemHandleSerializedItemHandleserializedItemHandleserialized_item_handle (输出控制) serialized_item → (handle)

Handle of the serialized item.

结果

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

可能的前趋

可能的后继

train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch, train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset, fwrite_serialized_itemfwrite_serialized_itemFwriteSerializedItemFwriteSerializedItemFwriteSerializedItemfwrite_serialized_item, send_serialized_itemsend_serialized_itemSendSerializedItemSendSerializedItemSendSerializedItemsend_serialized_item

另见

deserialize_dl_modeldeserialize_dl_modelDeserializeDlModelDeserializeDlModelDeserializeDlModeldeserialize_dl_model, apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelApplyDlModelapply_dl_model, train_dl_model_batchtrain_dl_model_batchTrainDlModelBatchTrainDlModelBatchTrainDlModelBatchtrain_dl_model_batch, train_dl_model_anomaly_datasettrain_dl_model_anomaly_datasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasetTrainDlModelAnomalyDatasettrain_dl_model_anomaly_dataset

模块

基础。该算子采用动态许可机制（详见《安装指南》）。所需模块取决于算子的具体使用场景：
3D计量学、光学字符识别/光学字符验证、匹配、深度学习推理

算子