Room window classification model construction method and room window classification method and system

Abstract

The invention discloses a room window classification model construction method and a room window classification method and system, and the method comprises the steps: obtaining a data set image, and dividing the data set image into a training set image and a test set image; sequentially inputting the training set images into a target detection network and a fine-grained classification network fortraining according to a preset iteration frequency, and storing the model file according to a preset interval to obtain a plurality of initial classification models; respectively inputting the test set image into the plurality of initial classification models for verification to obtain the accuracy of the plurality of initial classification models; and searching the maximum value of the accuracy from the accuracy of the plurality of initial classification models, and taking the initial classification model corresponding to the maximum value as a room window classification model. According to the method, the target detection network and the fine-grained classification network are combined to obtain the room window classification model, the model can accurately identify the subtle differences of the room windows, and the room window classification accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for building a room window classification model, a room window classification method and a system. Background technique [0002] At present, for the deep learning target detection industry, different types of object detection and classification are very mature, such as: different types of animal detection and classification such as cats and dogs, or different types of object detection and classification such as tables and chairs. However, for the detection and classification of objects with only subtle differences under the same category, it is still a technical problem that is difficult to solve in the industry. For example: detection and classification of different breeds of cats, detection and classification of different breeds of flowers, etc. [0003] In the field of housing and real estate, room windows are mainly divided into ordinary windows, bay windows...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a room window classification model building method and system, a room window classification method and system, to solve the problem of low room window classification accuracy in the prior art

Images