This work targets the commonly used FPGA (field-programmable gate array) devices as the hardware platform for DNN edge computing. We focus on DNN quantization as the main model compression technique. The novelty of this work is: We use a quantization method that supports multiple precisions along the intra-layer dimension, while the existing quantization methods apply multi-precision quantization along the inter-layer dimension. The intra-layer multi-precision method can uniform the hardware configurations for different layers to reduce computation overhead and at the same time preserve the model accuracy as the inter-layer approach. Our proposed ILMPQ DNN quantization framework achieves 70.73 Top1 accuracy in ResNet-18 on the ImageNet dataset. We also validate the proposed MSP framework on two FPGA devices i.e., Xilinx XC7Z020 and XC7Z045. We achieve 3.65x speedup in end-to-end inference time on the ImageNet, compared with the fixed-point quantization method.
@article{arxiv.2111.00155,
title = {ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA},
author = {Sung-En Chang and Yanyu Li and Mengshu Sun and Yanzhi Wang and Xue Lin},
journal= {arXiv preprint arXiv:2111.00155},
year = {2021}
}
Comments
Accepted by CogArch 2021: 5th Workshop on Cognitive Architectures