Title | ||
---|---|---|
LSFQ: A Low-Bit Full Integer Quantization for High-Performance FPGA-Based CNN Acceleration |
Abstract | ||
---|---|---|
The effective implementation of quantization depends not only on the specific task but also on the hardware resources. This article presents a hardware-aware customized quantization method for convolutional neural networks. We propose a learnable parameter soft clipping full integer quantization (LSFQ), which includes weight and activation quantization with the learnable clipping parameters. Moreo... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/MM.2021.3134968 | IEEE Micro |
Keywords | DocType | Volume |
Quantization (signal),Convolutional neural networks,Design automation,Computer architecture,Field programmable gate arrays,Training data,Neural networks,Accelerator architectures | Journal | 42 |
Issue | ISSN | Citations |
2 | 0272-1732 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhenshan Bao | 1 | 0 | 2.03 |
Guohang Fu | 2 | 0 | 0.34 |
Wenbo Zhang | 3 | 0 | 2.03 |
Zhan Kang | 4 | 0 | 1.01 |
Junnan Guo | 5 | 0 | 0.34 |