Semi-supervised learning image classification method and system, storage medium and computer equipment

Abstract

The invention provides a semi-supervised learning image classification method, which comprises the following steps of: creating a classification task, and triggering a training request of the classification task based on a plurality of sample data added to the classification task; in response to the training request, calling a large model to train the plurality of sample data so as to learn and obtain a target small model; wherein the large model is a pre-trained fixed model; and performing feature extraction on a to-be-detected image through the large model, and inputting a first output result of the large model to the target small model to obtain a second output result of the target small model after classification reasoning. The invention further provides a semi-supervised learning image classification system, a storage medium and computer equipment. Therefore, the classification model can be obtained through training and learning of a small amount of sample data, the threshold of artificial intelligence tasks is lowered, and actual operation experience service can be provided for artificial intelligence popularization education.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an image classification method, system, storage medium and computer equipment of semi-supervised learning. Background technique [0002] In recent years, artificial intelligence has developed rapidly, and artificial intelligence products are everywhere. Many primary and secondary schools have launched artificial intelligence popularization courses, focusing on broadening their learning horizons, enhancing students' interest in learning and technology, and cultivating their creative abilities. However, the threshold for artificial intelligence is high, and teachers lack practical educational materials. Ordinary paper textbooks, teacher explanations, and even learning videos make it difficult for students to gain a deep understanding of artificial intelligence. [0003] Generally speaking, to implement a classification task based on artificial intelligence, it is n...

AI Technical Summary

Problems solved by technology

Therefore, the existing artificial intelligence science education lacks a practical operation, a way to develop artificial intelligence models, or a science education tool

[0004] In summary, there are many problems in the actual use of existing methods, so it is necessary to improve

Images