LPYOLO: Low Precision YOLO for Face Detection on FPGA


Creative Commons License

Gunay B., Okcu S. B., Bilge H. Ş.

8th World Congress on Electrical Engineering and Computer Systems and Science, EECSS 2022, Prague, Czech Republic, 28 - 30 July 2022 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.11159/mvml22.108
  • City: Prague
  • Country: Czech Republic
  • Keywords: Face Detection, FPGA, Quantized Neural Networks, TinyYolo
  • Gazi University Affiliated: Yes

Abstract

© 2022, Avestia Publishing. All rights reserved.In recent years, number of edge computing devices and artificial intelligence applications on them have advanced excessively. In edge computing, decision making processes and computations are moved from servers to edge devices. Hence, cheap and low power devices are required. FPGAs are very low power, inclined to do parallel operations and deeply suitable devices for running Convolutional Neural Networks (CNN) which are the fundamental unit of an artificial intelligence application. Face detection on surveillance systems is the most expected application on the security market. In this work, TinyYolov3 architecture is redesigned and deployed for face detection. It is a CNN based object detection method and developed for embedded systems. PYNQ-Z2 is selected as a target board which has low-end Xilinx Zynq 7020 System-on-Chip (SoC) on it. Redesigned TinyYolov3 model is defined in numerous bit width precisions with Brevitas library which brings fundamental CNN layers and activations in integer quantized form. Then, the model is trained in a quantized structure with WiderFace dataset. In order to decrease latency and power consumption, on-chip memory of the FPGA is configured as a storage of whole network parameters and the last activation function is modified as rescaled HardTanh instead of Sigmoid. Also, high degree of parallelism is applied to logical resources of the FPGA. The model is converted to an HLS (High-Level-Synthesis) based application with using FINN framework and FINN-HLS library which includes the layer definitions in C++. Later, the model is synthesized and deployed. CPU of the SoC is employed with multithreading mechanism and responsible for preprocessing, postprocessing and TCP/IP streaming operations. Consequently, 2.4 Watt total board power consumption, 18 Frames-Per-Second (FPS) throughput and 0.757 Mean-Average-Precision (mAP) accuracy rate on Easy category of the WiderFace are achieved with 4 bits precision model.