A training method and device for a target classification model

Abstract

The embodiment of the present invention discloses a training method and device for a target classification model. The method includes: obtaining a training image and its corresponding calibration information; The first binary feature extraction operation obtains the corresponding output image; if the convolution layer is a binary convolution layer, the first binary feature extraction operation includes: the first binary feature extraction operation and preset dimension transformation Operation; the input image corresponding to the first convolutional layer is the training image, and the input image corresponding to the other convolutional layers is the output image corresponding to the previous convolutional layer; use the feature classification layer of the model and the last convolutional layer For the corresponding output image, determine the prediction detection information of the training image corresponding to the output image; combine the calibration detection information corresponding to each training image, adjust the model parameters, and determine the target binary classification model to achieve high recognition and detection accuracy and calculation A small target classification model.

Description

technical field [0001] The present invention relates to the technical field of data processing, and in particular, to a training method and device for a target classification model. Background technique [0002] Most of the current visual application scenarios use a detection and recognition scheme based on a Convolutional Neural Network (Convolutional Neural Network) model to perform relevant detection and recognition on the images collected for the target scene. For example: online image classification and recognition, and application scenarios such as recognition and detection of objects contained in images. [0003] Compared with the image detection and recognition scheme, the detection and recognition scheme based on convolutional neural network has the advantages of high accuracy and strong generalization ability. However, in the detection and identification scheme based on convolutional neural network, floating-point parameters are generally used in the convolutional...

AI Technical Summary

Problems solved by technology

However, in the detection and recognition scheme based on the convolutional neural network, the convolutional neural network generally uses floating-point parameters for related operations, resulting in high computing requirements, such as: a large amount of calculation, high hardware requirements and high storage requirements.

This has limited the popularity and use of detection and recognition schemes based on convolutional neural networks.

Images