Comparison of performance of optimized HSI CNN models on desktop and embedded platforms

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F21%3A00009863" target="_blank" >RIV/46747885:24220/21:00009863 - isvavai.cz</a>
Alternative codes found
RIV/46747885:24220/21:00008992
Result on the web
<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9542900" target="_blank" >https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9542900</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.23919/AE51540.2021.9542900" target="_blank" >10.23919/AE51540.2021.9542900</a>

Result language
angličtina
Original language name
Comparison of performance of optimized HSI CNN models on desktop and embedded platforms
Original language description
We compare different platforms for inference of convolutional neural networks in this paper. We trained various neural networks to determine the material in the source hyperspectral cube. Then we convert them to inference format and compare the inference results. We used tools under Xilinx Vitis AI for FPGA implementation. We try to minimize the size of the proposed networks by pruning them and provide further comparisons. FPGA platforms show to be energy efficient but still slower than a graphics card in terms of performance.
Czech name
—
Czech description
—

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)