@inproceedings{WOS:000641147900105,
title = {TL-TensorFlow CNN model and dataset for electronic equipment},
author = {Calin Bira and Valentin-Gabriel Voiculescu},
editor = {M Vladescu and R Tamas and I Cristea},
doi = {10.1117/12.2572157},
issn = {0277-786X},
year = {2020},
date = {2020-01-01},
booktitle = {ADVANCED TOPICS IN OPTOELECTRONICS, MICROELECTRONICS AND
NANOTECHNOLOGIES X},
volume = {11718},
publisher = {SPIE-INT SOC OPTICAL ENGINEERING},
address = {1000 20TH ST, PO BOX 10, BELLINGHAM, WA 98227-0010 USA},
organization = {Minist Res & Innovat; Univ Politehnica Bucharest, Optoelectron Res Ctr;
Maritime Univ Constanta},
series = {Proceedings of SPIE},
abstract = {This paper proposes a solution for classification of electronics
laboratory equipment with emphasis on the electronic laboratory tools /
equipment. It uses transfer-learning applied to the pretrained
Inception-V3 network model. A study regarding the impact of small
retrain dataset is conducted to see its impact in transfer-learning over
Inception-V3 network model.},
note = {Conference on Advanced Topics in Optoelectronics, Microelectronics and
Nanotechnologies X, Constanta, ROMANIA, AUG 20-23, 2020},
keywords = {CNN; transfer learning; Inception-v3; classify electronic equipement},
pubstate = {published},
tppubtype = {inproceedings}
}
