Target detection full-process acceleration method and system based on Vitis stack

Abstract

The invention discloses a target detection full-process acceleration method and system based on a Vitis stack, and the method comprises the steps: firstly carrying out the fine adjustment of a network, then carrying out the quantification processing of a model through a vitis quantizer, and carrying out the compiling of the model through a vitis compiler, achieving the conversion of an original network model, and reducing the data size; data transformation storage and data type fixed-point processing are carried out on the host program data, so that the data parallelism degree is improved; then, task type parallel and data optimization instructions are performed on the whole process, and data operation can be accelerated; next, a hardware accelerator and a system file are respectively created through vivado and petalinux, a hardware platform is formed through vitis integration, and interactive transmission is carried out on a ps end and a pl end through an AXI bus; and finally, the optimization design of the previous steps is integrated to form full-process acceleration. According to the design, the throughput rate of deploying a neural network algorithm in an embedded field edge device can be increased, and a certain acceleration effect is achieved in the field of target detection.

Description

technical field [0001] The invention belongs to the fields of artificial intelligence technology and target detection technology, and in particular relates to a method and system for accelerating the whole process of target detection based on Vitis stack. Background technique [0002] At present, artificial intelligence is developing rapidly, and various types of neural network models continue to break through bottlenecks and performance compared with previous traditional neural network algorithms. However, in the ever-increasing amount of data, the acceleration of these software algorithms does not fully adapt to the growing applications. Therefore, a hardware accelerator is needed to accelerate the neural network algorithm by hardware. [0003] At present, hardware acceleration has a wide range of application scenarios in different fields and directions, as a major acceleration technology in the period of rapid development of artificial intelligence and integrated circuit...

AI Technical Summary

Problems solved by technology

However, the optimization of the whole process from data storage to network model calculation to result processing is still relatively small.

Images