Image feature extraction model training method and device, server and storage medium

Abstract

The embodiment of the invention discloses a training method and device of an image feature extraction model, a server and a storage medium, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like. According to the embodiment of the invention, the image feature of the training sample and the image feature extraction model can be obtained, the image feature extraction model comprises a convolution module and a global attention module, the image feature of the training sample is subjected to convolution operation through each parallel filter, and the image sub-feature corresponding to each parallel filter is obtained; and inputting all image sub-features into a global attention module to obtain image features with global attention, adjusting a convolution module according to the image features with global attention to obtain an adjusted convolution module, and obtaining a trained image feature extraction model according to the adjusted convolution module and a preset loss function. According to the scheme, the filters can perceive and influence one another in the training process, and the training efficiency is improved.

Description

technical field [0001] The present application relates to the field of computers, in particular to a training method, device, server and storage medium for an image feature extraction model. Background technique [0002] With the development of deep learning technology, the application of image feature extraction based on convolutional neural network model is becoming more and more extensive. The convolutional neural network model is filtered through filters to perform feature expression to extract image features. [0003] However, to extract image features through a convolutional neural network model, it is necessary to input the image into the neural network model, and then adjust the parameters of the neural network model through iterative training, and the training efficiency is low. Contents of the invention [0004] Embodiments of the present application provide a training method, device, server, and storage medium for an image feature extraction model, which can en...

AI Technical Summary

Problems solved by technology

[0003] However, image feature extraction through the convolutional neural network model requires inputting the image into the neural network model, and then adjusting the parameters of the neural network model through iterative training, and the training efficiency is low.

Images