Image processing method and device

Abstract

The present application provides an image processing method, the method comprising: obtaining an input feature map; according to a plurality of stored basic convolution kernels and combination parameters, performing convolution on the input feature map to obtain an output feature map, wherein the The combination parameter is used to indicate the order in which the multiple basic convolution kernels are combined into a standard convolution kernel, and the size of the basic convolution kernel is smaller than the size of the standard convolution kernel; image processing is performed based on the output feature map , to get the processing result. The image processing method provided in the embodiment of the present application can reduce the storage space of the convolutional neural network model required for image processing.

Description

technical field [0001] The present application relates to artificial intelligence, and more specifically, to an image processing method and device in the field of image processing. Background technique [0002] With the continuous development of image processing technology and the continuous improvement of people's requirements for image display quality, convolutional neural networks (CNN) based on deep learning have developed rapidly in the field of image processing, especially in terminal equipment ( For example, there are more and more applications on mobile phones, cameras, smart homes, and self-driving cars, such as face recognition, object detection, and scene segmentation. [0003] Usually, the high-precision convolutional neural network has a large amount of parameters and calculations. Commonly used convolutional neural network models need to occupy hundreds of megabytes of storage space and billions of calculations, while the memory and computing power of terminal ...

AI Technical Summary

Problems solved by technology

[0003] Usually, the high-precision convolutional neural network has a large amount of parameters and calculations. Commonly used convolutional neural network models need to occupy hundreds of megabytes of storage space and billions of calculations, while the memory and computing power of terminal devices Resources are very limited, do not have strong computing power and large cache, making it difficult to deploy high-precision convolutional neural networks on terminal devices

Images