Data processing method and device, medium and computing equipment

Abstract

The embodiment of the invention provides a data processing method. The data processing method comprises the following steps: acquiring a plurality of sample images; Adding a label to the plurality ofsample images, adding a positive sample label to the sample image including a predetermined feature, and adding a negative sample label to the sample image not including the predetermined feature; Establishing a neural network classification model based on an attention mechanism; And training the neural network classification model by using the sample image added with the label to obtain an optimal classification model. According to the scheme, an attention mechanism is introduced into a neural network classification model as an initial training model; A neural network classification model with an attention mechanism introduced in the training process can extract discriminative features which are more beneficial to distinguishing whether the image is a positive sample or a negative sample,and then an optimal classification model which can more sensitively and accurately judge whether the image contains predetermined features or not is obtained. The embodiment of the invention furtherprovides a data processing device, a medium and computing equipment.

Description

technical field [0001] Embodiments of the present invention relate to the field of deep learning, and more specifically, embodiments of the present invention relate to data processing methods, devices, media, and computing devices. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Existing image classification models are good at classifying images with clear and regular features, but poor at classifying images with fuzzy and irregular features. When the images are very large, it is often impossible to obtain accurate classification results of whether such images contain predetermined features using existing image classification models. Contents of the invention [0004] In the prior art, it is a very troublesome process to achieve accurate classification of images with ...

AI Technical Summary

Problems solved by technology

[0003] Existing image classification models are good at classifying images with clear and regular features, but poor at classifying images with fuzzy and irregular features. When the image is very large, it is often impossible to obtain an accurate classification result of whether such an image contains predetermined features using the existing image classification model

Images