Acceleration of deep neural networks with the Intel Neural Compute Stick 2

A tétel rövid nézete
dc.contributor.advisorSütő, József
dc.contributor.authorGao, Tianyu
dc.contributor.departmentDE--Informatikai Kar
dc.date.accessioned2025-02-22T22:58:31Z
dc.date.available2025-02-22T22:58:31Z
dc.date.created2024-10-31
dc.description.abstractThis research investigates the efficiency of using the Intel® Neural Compute Stick 2 (NCS2) on the Raspberry Pi platform to accelerate deep learning neural networks. The motivation behind this study is to enable the real-time operation of complex neural networks in embedded systems, potentially reducing the cost of deep learning neural network deployment and expanding industrial applications. Results indicate that, for the specific models used in this experiment, NCS2 improves image recognition performance by approximately 500% and realtime object tracking by around 1500% to 1300%. These findings highlight the significant performance gains NCS2 offers in constrained hardware environments. This suggests its potential for real-time applications such as autonomous systems and smart surveillance. Future research could expand this approach to other low-power devices and refine the models for specific real-world applications.
dc.description.courseMérnökinformatikus
dc.description.degreeBSc/BA
dc.format.extent62
dc.identifier.urihttps://hdl.handle.net/2437/387482
dc.language.isoen
dc.rights.accessHozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.
dc.subjectIntel® Neural Compute Stick 2, Raspberry Pi, deep learning, OpenVINO™, Deep SORT, neural networks, real-time object tracking, image recognition
dc.subject.dspaceInformatics
dc.titleAcceleration of deep neural networks with the Intel Neural Compute Stick 2
Fájlok
Eredeti köteg (ORIGINAL bundle)
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
thesis.pdf
Méret:
1.59 MB
Formátum:
Adobe Portable Document Format
Leírás:
thesis
Megjelenítés
Engedélyek köteg
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
license.txt
Méret:
1.95 KB
Formátum:
Item-specific license agreed upon to submission
Leírás:
Letöltés
Gyűjtemények
Theses (IK)