.png){kind=icon}
.png){kind=icon}
Return
Single-Step Hardware-Aware Neural Network Quantization With Mixed Precision
.png){kind=icon}
PRE
AI
DOI：10.1109/TC.2026.3666546.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Quantization is a neural network compression technique that effectively improves the deployment performance on inference hardware. Fixed-point quantization methods use the same bit-width for all layers in the network, which leads to difficulties in balancing compression rate and accuracy loss. Therefore, mixed-precision quantization has recently been proposed. The major challenge of the mixed-precision quantization is to select the quantization bit-widths of each layer in network to simultaneously meet the requirements of minimizing accuracy loss and hardware resource consumption. In this paper, we present a Single-Step Hardware-Aware Quantization (SHQ) method. It can calculate the resource consumption of hardware such as Field Programmable Gate Arrays (FPGAs) before actual deployment and find effective quantization schemes by just single step, different from common software-hardware two-step approaches with large workload and time-consuming. Genetic algorithm is combined with SHQ to search quantization schemes with low hardware resource usage and high accuracy. In addition, the correlation between hardware resource cost and qualitative indicators of proxy signal has been analyzed to bring computer-aided design insights of neural network accelerators. Experiments of full-pipeline accelerator deployment on FPGAs platforms show that our approach saves 39% of Digital Signal Processors (DSP) and 59% of Block Random Access Memory (BRAM) usage on MobileNet compared to full 8-bit quantization, while the accuracy drops by only 0.56%. The source code about our method can be found at this link: https://github.com/hujie369/SHQ.
Keywords:
Neural network
quantization
genetic algorithm
hardware-aware