Method and device for training a multi-label classification model

Abstract

The invention provides a method and a device for training a multi-label classification model, which can dynamically learn image features, enable a feature extraction network to better adapt to task requirements, and are good in multi-label classification effect. The method comprises the steps of determning n samples and a label matrix Yc * n corresponding to the n samples in a training data set, wherein an element yi * j in the label matrix Yc * n represents whether an ith sample contains an object indicated by a jth label or not, and c represents the number of labels related to the samples; extracting a feature matrix Xd * n of the n samples by using a feature extraction network;utilizing a feature mapping network to obtain a prediction tag matrix of the feature matrix Xd * n, wherein theprediction tag matrix is obtained by using the feature mapping network; and obtaining a prediction tag matrix of the feature matrix Xd * n. Elements in the DA00033902000001. TIF are shown in the specification. The invention also discloses a preparation method of the optical glass. The optical glass is characterized in that the optical glass is prepared from the optical glass, the optical glass and the like; a confidence representing that the i-th sample comprises an object indicated by the j-th tag; According to the label matrix Yc * n and the prediction label matrix, obtaining a predictionlabel matrix Yc * n according to the prediction label matrix Yc * n and the prediction label matrix Yc * n, and updating the weight parameter Z and the feature mapping matrix Mc * d, and training themulti-tag classification model.

Description

technical field [0001] The present application relates to the computer field, and more specifically, to a method and device for training a multi-label classification model in the computer field. Background technique [0002] With the improvement of the processing performance of smart phones, more and more applications have put forward requirements for image recognition. For example, in the process of taking pictures with a mobile phone, if the smartphone can accurately identify objects within the shooting range, it can perform targeted calculations on its color and shape, thereby improving the shooting effect. In the machine learning of intelligent systems, the training of recognizing objects in images has become a very important aspect. Generally speaking, machine learning is to set labels for a large number of existing images for the objects contained in them, and then continuously adjust the recognition parameters through computer self-evolution to gradually improve the ...

AI Technical Summary

Problems solved by technology

But this method needs to extract the features of the image first, and then calculate the feature mapping matrix according to the features of the image

After the features of the image are extracted, the features of the image are fixed, so it is not possible to dynamically learn the feature information of the input image according to the label.

Images