Accuracy compensation method, system and storage medium for feature map scaling

Abstract

The present application discloses an accuracy compensation method for feature mapping scaling, which includes the following steps: obtaining mapping data of original features and target features, wherein the mapping data at least includes bit width, number of channels, number of feature horizontal pixels and feature vertical pixels Number; according to the original feature map and the number of feature horizontal pixels and the number of feature vertical pixels of the target feature, calculate the target feature in the horizontal direction and the number of feature vertical pixels based on the bit width on each channel indicated by the channel number. Interpolation coordinates in the vertical direction; according to the respective interpolation coordinates of the original feature map and the target feature, calculate the interpolation of the original feature at each interpolation coordinate of the target feature based on the bit width on each channel indicated by the channel number Weight; determine the target feature map according to the pixel value of the original feature at each position and the interpolation weight at each interpolation coordinate. The application also discloses the corresponding computer system and storage medium.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an accuracy compensation method, system and storage medium for feature map scaling in a bilinear scaling algorithm. Background technique [0002] In the field of computer vision, the research of deep neural network has received extensive attention, especially the convolutional neural network has been developed rapidly. Compared with existing technologies, convolutional neural networks have greatly improved the accuracy of many applications such as face detection and recognition, speech recognition, and object classification. The accuracy of some of these applications has even exceeded the average human level. This makes it possible to put electronic products based on convolutional neural network technology into real life. In conventional applications, completing a convolutional neural network calculation often requires billions (giga) or even trillion (tera) times of multiplicati...

AI Technical Summary

Problems solved by technology

In conventional applications, one billion (giga) or even trillion (tera) multiplication and addition operations are often required to complete a convolutional neural network calculation, which makes the amount of data interaction high.

Images