mv_machine_learning: face recognition: allow 5 set per a label 04/286304/2
authorInki Dae <inki.dae@samsung.com>
Tue, 3 Jan 2023 09:43:01 +0000 (18:43 +0900)
committerInki Dae <inki.dae@samsung.com>
Tue, 3 Jan 2023 10:16:40 +0000 (19:16 +0900)
commit3dda176c70a5d056628705644a3839b571dbc3ae
treed3ae62c08717c026cce07cd2287b9298c1b4c981
parent25831f7b4dfb5442e87a978fdc867df66cbd4fe8
mv_machine_learning: face recognition: allow 5 set per a label

[Issue type] New feature

Added a new feature that it allows maximum 5 set of feature vector
per a label. In case of few-shot leanring based on KNN algorthm,
Feature vector set more than 5 aren't needed.

This is a temporary solution so I will introduce a feature vector priority
based solution if NNTrainer is ready for this later.

Change-Id: I57d24f36101b354ea2e0fed8134f99a31e32307e
Signed-off-by: Inki Dae <inki.dae@samsung.com>
mv_machine_learning/face_recognition/include/nntrainer_dsm.h
mv_machine_learning/face_recognition/src/face_recognition.cpp
mv_machine_learning/face_recognition/src/nntrainer_dsm.cpp
mv_machine_learning/training/include/data_set_manager.h
mv_machine_learning/training/src/data_set_manager.cpp