Comparison of Performance of Optimized HSI CNN models on Desktop and Embedded Platforms
| dc.contributor.author | Čech, Jiří | |
| dc.contributor.author | Rozkovec, Martin | |
| dc.contributor.editor | Pinker, Jiří | |
| dc.date.accessioned | 2021-10-27T09:07:47Z | |
| dc.date.available | 2021-10-27T09:07:47Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract-translated | 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. | en |
| dc.description.sponsorship | SGS-2019-3017 | en |
| dc.format | 4 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | 2021 International Conference on Applied Electronics: Pilsen, 7th – 8th September 2021, Czech Republic, p. 29-32. | en |
| dc.identifier.isbn | 978–80–261–0972–3 (Print) | |
| dc.identifier.isbn | 978–80–261–0973–0 (Online) | |
| dc.identifier.issn | 1803–7232 (Print) | |
| dc.identifier.issn | 1805–9597 (Online) | |
| dc.identifier.uri | http://hdl.handle.net/11025/45560 | |
| dc.language.iso | en | en |
| dc.publisher | University of West Bohemia | en |
| dc.rights | © University of West Bohemia, 2021 | en |
| dc.rights.access | openAccess | en |
| dc.subject | hyperspektrální zobrazování | cs |
| dc.subject | neuronové sítě | cs |
| dc.subject | Xilinx FPGA | cs |
| dc.subject | Vitis AI | cs |
| dc.subject | DPU | cs |
| dc.subject.translated | hyperspectral imaging | en |
| dc.subject.translated | neural networks | en |
| dc.subject.translated | Xilinx FPGA | en |
| dc.subject.translated | Vitis AI | en |
| dc.subject.translated | DPU | en |
| dc.title | Comparison of Performance of Optimized HSI CNN models on Desktop and Embedded Platforms | en |
| dc.type | conferenceObject | en |
| dc.type | konferenční příspěvek | cs |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
Files
Original bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- Comparison_of_Performance_of_Optimized_HSI_CNN_models_on_Desktop_and_Embedded_Platforms.pdf
- Size:
- 818.44 KB
- Format:
- Adobe Portable Document Format
- Description:
- Plný text
License bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: