Method, system and equipment for accelerating image processing and storage medium

Abstract

The invention provides a method, a system and equipment for accelerating image processing and a storage medium. The method comprises the following steps: dividing obtained picture data into data blocks, and executing the following steps during convolution operation of each data block: carrying out picture data conversion and convolution kernel data conversion on the data blocks to respectively obtain a picture data conversion item and a convolution kernel data conversion item; and accelerating the convolution operation of the image data conversion item and the convolution kernel data conversion item in the data block through a GPU acceleration unit, and performing inverse transformation on the result of the convolution operation to obtain a calculation result. The invention has the advantages that the image convolution operation speed can be greatly increased, and the performance requirement during reasoning is met. In addition, the invention also provides an optimal data partitioning structure for executing the method disclosed by the invention, so that further implementation of the method disclosed by the invention is facilitated.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, system, device and storage medium for accelerating image processing. Background technique [0002] With the rapid development of technologies such as the Internet, big data, and cloud computing, the development of artificial intelligence (AI) has advanced by leaps and bounds, and a series of application products have emerged in various fields such as speech recognition, image recognition, intelligent control, and complex computing. It is also widely used in all walks of life, and image processing has always been a research hotspot in the field of artificial intelligence. For example, automatic driving of cars can directly control the driving behavior of cars on the road through the collection and processing of real-time road condition image information; In terms of face recognition, by comparing the data in the information database, the facial features ...

AI Technical Summary

Problems solved by technology

like figure 1 As shown, it is the process of using the 3*3 convolution kernel in Resnet50 to process images in the prior art. The process includes: firstly, set the loop according to the original data of the input NHWC. At this time, the outer loop is [N, H, W, Oc], the inner loop is [kh, kw, Ic], and then the calculation convolution matrix is ​​multiplied. At this time, the main calculation rule becomes kh*kw*(NHW, Ic)x(Ic, Oc), after kh , kw, and Ic directions are continuously accumulated to obtain the final result. The whole process needs to divide the data into blocks and send them to the calculation thread of the GPU to achieve accelerated calculation. In this calculation method, a large number of matrix multiplication operations are required, resulting in a slow calculation rate. Performance requirements when reasoning is difficult

Images