General hardware accelerator system platform oriented to YOLO algorithm and capable of being rapidly deployed

Abstract

A universal hardware accelerator system platform oriented to a YOLO algorithm and capable of being rapidly deployed belongs to the technical field of computers, considers the deployment requirements of the YOLO target detection algorithm on rapidness, high performance and low power consumption, and has a wide application scene. The platform is composed of an ARM subsystem, an FPGA subsystem and an off-chip memory, the ARM subsystem is responsible for parameter initialization, image preprocessing, model parameter preprocessing, data field address allocation, FPGA accelerator driving and image post-processing, and the FPGA subsystem is responsible for high-density calculation of a YOLO algorithm. After the platform is started, a YOLO algorithm configuration file is read, accelerator driving parameters are initialized, a to-be-detected image is preprocessed, then model weight and bias data are read, quantization, fusion and reordering are executed, an FPGA subsystem is driven to execute model calculation, and a calculation result is post-processed to obtain a target detection image. According to the method, the YOLO algorithm can be quickly deployed on the premise of high performance and low power consumption.

Description

technical field [0001] The invention belongs to the field of computer technology, and in particular relates to a general hardware accelerator system platform that can be quickly deployed for YOLO algorithm. Background technique [0002] With the improvement of computer computing power and the development of big data, Convolutional Neural Network (CNN) has become the mainstream in the field of computer vision. As an important branch of CNN-based computer vision, target detection algorithm, especially YOLO (You Only Look Once) series of algorithms show excellent results in terms of speed and accuracy, and are widely used in many fields, such as robot vision, security monitoring, autonomous driving, virtual reality, etc. [0003] The YOLO algorithm is constantly developing in the direction of intensive computing, large amount of data and complex structure. At the same time, the version update and iteration are fast, which makes the deployment of the algorithm more difficult, an...

AI Technical Summary

Problems solved by technology

[0004] Existing deployment solutions are generally based on CPU, GPU, FPGA, or ASIC platforms, but general-purpose processor CPUs cannot meet high-performance requirements, GPU acceleration delays are high, power consumption is high, and AISC development costs are high, so it has programmable, high parallelism, FPGAs with low power consumption have received widespread attention

However, as the complexity of the YOLO algorithm is getting higher and higher, and the update iteration is getting faster and faster, the FPGA accelerator of the current convolutional neural network highlights the problems of high deployment difficulty and long development cycle.

Images