Circuit for processing data, image processing system, and method and apparatus for processing data

Abstract

The embodiments of the invention disclose a circuit for processing data, an image processing system, and a method and apparatus for processing data. The circuit comprises a control unit and N processing units. The control unit and each processing unit among the N processing units are connected with a data transmission unit, each processing unit is used for processing the same data output successively by the data transmission unit, and the output end of an i-th processing unit among the N processing units is connected with the input end of an (i+1)th processing unit, wherein N is an integer greater than 1, and the value scope of i is an integer ranging from 1 to N-1. The control unit is used for, when it is determined that data to be processed output by the data transmission unit is 0, controlling the N processing units to be all at a closed state. The circuit, the system, the method and the apparatus provided by the embodiments of the invention can reduce circuit power consumption while realizing convolution operation.

Description

technical field [0001] The present invention relates to a convolutional neural network (Convolution Neural Network, CNN), in particular to a circuit for processing data in CNN, an image processing system, a method and a device for processing data. Background technique [0002] Neural networks and deep learning algorithms have been very successfully applied and are in the process of rapid development. The industry generally expects that new computing methods will help realize more common and complex intelligent applications. CNN has made outstanding achievements in the field of image recognition applications in recent years. Therefore, the industry has begun to pay attention to the optimization and high-efficiency realization of CNN algorithms. Companies such as Facebook, Qualcomm, Baidu, and Google have invested in CNN. Research on optimization algorithms. [0003] Generally, convolution operations in CNNs are implemented using traditional pipeline solutions. The specific ...

AI Technical Summary

Problems solved by technology

Turning off different circuits separately has a relatively large overhead on the control circuit, and the implementation benefit is relatively small. Therefore, a more efficient circuit layout is urgently needed to realize the control of reducing power consumption.

Images