OPTIMIZATIONS OF DEEP LEARNING OBJECTS DETECTION MODELS FOR INFERENCE ACCELERATION ON GENERAL-PURPOSE AND HARDWARE-ACCELERATED SINGLE-BOARD PLATFORMS
Background. Description and preparation of modern approaches for deep learning object detection models are provided. Deep learning frameworks for model training and inference, such as TensorFlow and TensorFlow Lite, are used as bases. The concepts of deep learning model optimization are analyzed....
Saved in:
| Main Authors: | Dmytro Myroniuk, Bohdan Blahitko |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ivan Franko National University of Lviv
2025-03-01
|
| Series: | Електроніка та інформаційні технології |
| Subjects: | |
| Online Access: | http://publications.lnu.edu.ua/collections/index.php/electronics/article/view/4782 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Research on Life Test and Evaluation Technology of Power Supply Board of EMUs Based on Accelerated Degradation
by: SHAO Zhihe, et al.
Published: (2018-01-01) -
Innovative Hardware Accelerator Architecture for FPGA-Based General-Purpose RISC Microprocessors
by: Ehsan Ali
Published: (2025-01-01) -
BALI—A Benchmark for Accelerated Language Model Inference
by: Lena Jurkschat, et al.
Published: (2025-01-01) -
Suitability of common single circuit boards for sensing and actuating in smart textiles
by: Guido Ehrmann, et al.
Published: (2020-12-01) -
OPENSTACK ON RASPBERRY PI: A SWOT ANALYSIS OF DEPLOYING A CLOUD COMPUTING PLATFORM ON SINGLE-BOARD COMPUTERS
by: Lyberius Ennio F. Taruc, et al.
Published: (2025-06-01)