Image processing method and device, electronic equipment and computer storage medium

Abstract

The embodiment of the invention discloses an image processing method and device, electronic equipment and a computer storage medium. The method comprises the steps: obtaining a to-be-processed image;inputting the to-be-processed image into a target neural network for processing to obtain an image processing result; wherein the target neural network is obtained by the following steps: grouping network channels in a first neural network according to the similarity among the network channels in the first neural network; determining a reference network channel in at least one network channel group in the first neural network according to the packet; according to the network channels except the reference network channel in the at least one network channel group and the similarity between the network channels and the reference network channel in the network channel group, the network channels in the at least one network channel group are determined; and updating the weight of the referencenetwork channel in the network channel group, and eliminating the network channels except the reference network channel in the network channel group to obtain the target neural network. The embodimentof the invention is applied to the mobile terminal and can ensure the precision of image processing.

Description

technical field [0001] The invention relates to computer vision technology, in particular to an image processing method and device, electronic equipment and a computer storage medium. Background technique [0002] In recent years, deep convolutional neural networks have made remarkable progress in the application of computer vision. Most deep convolutional neural networks, such as VGG, ResNet, etc., need to be executed on a GPU with a large amount of memory and computing power. Neural networks are difficult to apply on mobile terminals with limited computing resources. [0003] Network compression technology, as the technical basis of deep convolutional neural network applications in mobile terminals, has received more and more attention. Among them, the pruning technology to reduce network redundancy can reduce the size of the neural network by directly reducing the unimportant network channels in the network. Using the neural network processed by the existing pruning me...

AI Technical Summary

Problems solved by technology

Using the neural network processed by the existing pruning method for image processing, although the amount of calculation is reduced, but due to the serious decline in network accuracy, the accuracy of image processing is reduced, making it difficult for the obtained image to meet the needs of practical applications.

Images