Convolution processing method and system applied to convolutional neural network and related components

Abstract

The invention discloses a convolution processing method applied to a convolutional neural network. The convolution processing method comprises the steps of obtaining a target operation object; whereinthe target operation object is specifically an input feature; performing side window convolution calculation on the target operation object to obtain calculation results in multiple directions; and performing cross entropy optimization processing on the calculation results in the multiple directions to obtain a convolution result of the target operation object. According to the method, performance loss caused by convolution operation with the convolution kernel as the central point in an original convolutional neural network is solved, the ability of the convolution operation to acquire moregeneralized features of data is improved by comprehensively analyzing side window convolution operation in multiple directions, and thus the performance of the convolutional neural network is improved. Correspondingly, the invention further discloses a convolution processing system and device applied to the convolutional neural network and a readable storage medium.

Description

technical field [0001] The present invention relates to the field of deep learning, in particular to a convolution processing method, system and related components applied to a convolutional neural network. Background technique [0002] In deep learning, convolutional neural network is a relatively important type of neural network. Its biggest feature is convolution operation, which is often used in the training process to extract different features through convolution, and then combine all these features organically. Make decisions accordingly. [0003] However, due to the traditional convolution operation, the center point of the convolution kernel is selected for the corresponding multiplication and addition operation. When a certain pixel is on the boundary, placing the center of the window on the pixel to perform the convolution operation will blur the edge, which will reduce the feature. Distinguishability, coupled with convolutional neural networks usually have many ...

AI Technical Summary

Problems solved by technology

[0003] However, due to the traditional convolution operation, the center point of the convolution kernel is selected for the corresponding multiplication and addition operation. When a pixel is on the boundary, placing the center of the window on the pixel to perform the convolution operation will blur the edge, which will reduce the feature. Distinguishability, coupled with convolutional neural networks usually have many layers, each layer has multiple convolution kernel filters, and the layers are connected to form a directed acyclic graph. Such a centrally located convolution will intensify the The situation where the resolution decreases, thereby reducing the performance of the convolutional neural network

Images