Open CL Based FGPA Implementation Of Object Detection Using Convolutional Neural Network

Lee, Zhao Lun (2018) Open CL Based FGPA Implementation Of Object Detection Using Convolutional Neural Network. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text (24 Pages) Opencl Based FPGA Implementation Of Object Detection Using Convolutional Neural Network.pdf - Submitted Version Download (246kB)

Abstract

Deep Convolutional Neural Network (CNN) algorithm has recently gained popularity in many applications such as image classification,video analytic,object recognition and segmentation.Being compute-intensive and memory expensive,CNN computations are common accelerated by GPUs with high power dissipations.Recent studies show implementation of CNN on FPGA and it gain higher advantage in term of energy-efficient and flexibility over Software-configurable-GPUs.However,unlike high-end GPU which have large memory on chip,FPGA on the other hand,has limited memory on chip and could have fatal bottleneck if the kernel was not properly pipelined.Thus, in this work,a FPGA accelerator with a new architecture of deeply pipelined OpenCL kernel is proposed to optimize the accelerator throughput under FPGA constraints such as memory capacity and clock frequency.The proposed framework is verified by implement Tiny-Yolo-V2 on the DE1-SoC.The design development in this project is HLS approach to ease programming effort from writing complex RTL codes and provide fast verification through emulation and profiling tools provided in the OpenCL SDK v16.1.

Actions (login required)

View Item