HALCON Operator reference

HALCON Operator Reference / Deep Learning / Continual Learning

• HALCON Script
• .NET
• Python
• C++
• C

ClassesClasses | | Operators

extend_dl_continual_learningT_extend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning (Operator)

extend_dl_continual_learningT_extend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning — Extend a Continual Learning model with with new data.

Signature

extend_dl_continual_learning( : : DLModelHandle, DLDataset, GenParam : )

Herror T_extend_dl_continual_learning(const Htuple DLModelHandle, const Htuple DLDataset, const Htuple GenParam)

void ExtendDlContinualLearning(const HTuple& DLModelHandle, const HTuple& DLDataset, const HTuple& GenParam)

static void HOperatorSet.ExtendDlContinualLearning(HTuple DLModelHandle, HTuple DLDataset, HTuple genParam)

def extend_dl_continual_learning(dlmodel_handle: HHandle, dldataset: HHandle, gen_param: HHandle) -> None

Description

extend_dl_continual_learningextend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning extends a Continual Learning model DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle of 'type'"type""type""type""type" = 'classification'"classification""classification""classification""classification" with new data provided by DLDatasetDLDatasetDLDatasetDLDatasetdldataset. The new data can either contain new classes that the model should learn to predict, or new samples of an existing class to improve the model for that particular class. DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle learns from the provided data in a manner specific to Continual Learning. After calling extend_dl_continual_learningextend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning, the model will either be able to predict more classes or the internal knowledge of existing classes will have been extended, depending on the dataset provided. See Deep Learning / Continual Learning for further information.

DLDatasetDLDatasetDLDatasetDLDatasetdldataset must only contain new data which the model should learn. It is not necessary to provide data samples from previous Continual Learning training steps, because the model preserves previously learned classes. Besides extend_dl_continual_learningextend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning can be called with a DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle optimized for an AI ²-interface. As a result, you can extend your Continual Learning model directly on an edge device.

The operator expects a dataset that is preprocessed by the supplied procedure preprocess_dl_dataset. Changes made within the procedure to the path of the samples are not supported and lead to errors. extend_dl_continual_learningextend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning will change the ClassIDs of the provided DLDatasetDLDatasetDLDatasetDLDatasetdldataset internally to match the ClassIDs of the provided model. New unknown classes will receive a new and unused ClassID. The ClassID of known classes within DLDatasetDLDatasetDLDatasetDLDatasetdldataset will be changed to the ClassID given by the model. These changes are applied both to the provided DLDatasetDLDatasetDLDatasetDLDatasetdldataset dictionary and to all preprocessed samples on disk. This is required for correct evaluation.

The performance of the Continual Learning model can be evaluated using the procedure evaluate_dl_model. You can provide one or more datasets, containing all classes the model has been trained on or only a subset of those. It is strongly recommended to evaluate the model with test data corresponding to all classes and Continual Learning steps, so that the evaluation result accurately reflects the capabilities of the model on all relevant data.

The operator also recalculates the Out-of-Distribution threshold. Any threshold value previously set by the user will be overwritten. Confidence calibration is done only once (either in init_dl_continual_learninginit_dl_continual_learningInitDlContinualLearningInitDlContinualLearninginit_dl_continual_learning, if a dataset was provided, or in the first call to extend_dl_continual_learningextend_dl_continual_learningExtendDlContinualLearningExtendDlContinualLearningextend_dl_continual_learning) and not repeated. As more classes are added, the absolute confidence values will generally decrease.

GenParamGenParamGenParamgenParamgen_param is a dictionary for setting generic parameters. Currently no generic parameters are supported.

Attention

The operator makes changes to the samples of the provided dataset. If an error occurs during the changes, the dataset is incompletely adjusted and corrupted. It must then be re-read and pre-processed again. This is indicated by the operator's error message in the event of an error.

Note that the operator does not behave additively. Adding images of the same class in several calls does not result in an identical model compared to adding the same, combined images in a single call.

Execution Information

• Multithreading type: reentrant (runs in parallel with non-exclusive operators).
• Multithreading scope: global (may be called from any thread).
• Processed without parallelization.

This operator modifies the state of the following input parameters:

• DLModelHandleDLModelHandleDLModelHandleDLModelHandledlmodel_handle
• DLDatasetDLDatasetDLDatasetDLDatasetdldataset

During execution of this operator, access to the values of these parameters must be synchronized if it is used across multiple threads.

Parameters

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

Handle of a deep learning classification model initialized for Continual Learning.

DLDatasetDLDatasetDLDatasetDLDatasetdldataset (input_control, state is modified)  dict → HDict, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Dataset for new Continual Learning training step.

GenParamGenParamGenParamgenParamgen_param (input_control)  dict → HDict, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

Dictionary for generic parameters.

Default: []

Possible Predecessors

init_dl_continual_learninginit_dl_continual_learningInitDlContinualLearningInitDlContinualLearninginit_dl_continual_learning

Possible Successors

apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelapply_dl_model

Module

Deep Learning Professional

---

ClassesClasses | | Operators