A method and apparatus for training modelMethod and device for training a model

Abstract

The embodiment of the invention discloses a method and a device for training a model, and a method and a device for generating information. A specific embodiment of the method for training the model comprises the following steps of: obtaining a model, obtaining a training sample set, the training samples in the training sample set comprising a sample image and discrimination information and position information corresponding to the sample image, the discrimination information being used for indicating whether the corresponding sample image comprises an animal object, and the position information being information used for indicating the position of the animal object in the sample image; a machine learning algorithm is utilized, sample images included in training samples in a training sample set serve as input data, judgment information and position information corresponding to the input sample images serve as expected output data, and a recognition model is obtained through training. According to the embodiment, the training modes of the model are enriched, and the image processing efficiency can be improved by adopting the trained model.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a method and device for training a model, and a method and device for generating information. Background technique [0002] In the prior art, when the convolutional neural network is used to determine the position of the target object in the image, the image is usually input to the convolutional neural network model for positioning to realize the positioning of the target object in the image , and then obtain the position information of the target object in the image. [0003] However, for electronic devices such as computers, it is often impossible to know in advance whether the image contains the target object before the target object is located. In other words, the image input to the convolutional neural network for positioning may Contains the target object object, or may not contain the target object object. Contents of the invention [0...

AI Technical Summary

Problems solved by technology

[0003] However, for electronic devices such as computers, it is often impossible to know in advance whether the image contains the target object before the target object is located. In other words, the image input to the convolutional neural network for positioning may Contains the target object object, may also not contain the target object object

Images