Method and device for generating model and method and device for outputting information

Abstract

The embodiment of the invention discloses a method and device for generating a model and a method and device for outputting information. A specific embodiment of the method for generating the model comprises the steps of obtaining a training sample set; using machine learning algorithms, taking sample images in training samples included in the training sample set as input data of an initial model;and taking the sample discrimination information corresponding to the input sample image as first expected output data of the initial model, taking the sample attribute information corresponding to the input sample image as second expected output data of the initial model, and performing training to obtain an identification model. Therefore, the training mode of the model is enriched, the identification model obtained by the embodiment of the invention is used for judging whether any image contains the target object or not and determining the attribute information of the target object in theimage, and the identification speed can be improved.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to methods and devices for generating models and outputting information. Background technique [0002] In the prior art, the method of determining the attributes of a specific object in any image (such as the probability of belonging to a predetermined category, shape, etc.) is usually: first determine whether the above-mentioned specific object is included in the image; if the specific object is included, then further determine the above-mentioned Attributes of specific objects included in the image. [0003] As an example, in the application scenario of determining whether the face in the image is a male face or a female face, first, it is necessary to determine whether the image contains a human face object, and if so, then judge and classify it; if not If it contains, no classification judgment will be made. Or even if a classification result i...

AI Technical Summary

Problems solved by technology

Or, even if a classification result is obtained after the classification judgment (for example, the classification result indicating that the face in the image is a male face or a female face), since the image does not contain a human face object, the classification result does not have D

Images