Image identification method, device and system

Abstract

The invention discloses an image identification method. The method comprises the steps that CPUs establish communication protocols with algorithm accelerators according to received identification instructions; image data to be identified is sent to the algorithm accelerators according to the communication protocol; the algorithm accelerators use an image identification algorithm in a memory to process the image data to be identified, and an identification result is obtained; the CPUs receive the identification result which is returned by the algorithm accelerators. According to the method, theCPUs are connected with the algorithm accelerators, the image identification algorithm is operated by the algorithm accelerators to accelerate the image data to be identified, that is to say, the number of the CPUs is increased, the performance of processing various image identification algorithms by a system is effectively improved, and the whole performance of the system is further improved. The invention further discloses an image identification device and system which have the advantages above.

Description

technical field [0001] The present invention relates to the field of servers, in particular to an image recognition method, and also to an image recognition device and system. Background technique [0002] Image recognition is an important field of artificial intelligence. In the human image recognition system, the recognition of complex images is often realized through different levels of information processing. CNN (Convolutional Neural Network, Convolutional Neural Network) is a feed-forward neural network that can be applied to large-scale image recognition and other processing, which contains various model algorithms applied to different scenarios, that is, image recognition algorithms. efficient identification method. With more and more computing scenarios in daily life and more and more complex, users have higher and higher performance requirements for the system to process various model algorithms, that is, AI (Artificial Intelligence, artificial intelligence) perfo...

AI Technical Summary

Problems solved by technology

[0003] However, simply improving the performance of a single CPU node can no longer meet people's requirements for server AI performance, so it is necessary to increase the number of CPUs in the server to achieve the above goals

However, based on the limitations of current technology, it is very limited to expand the number of CPUs in a tightly coupled system, which cannot really improve the performance of the system in processing various image recognition algorithms, nor can it improve the overall performance of the system.

Images