Image classification method and system based on neural network optimization of gradient direction parameters

Abstract

The invention discloses an image classification method and system based on a neural network optimized for gradient direction parameters, acquires an image data set, and preprocesses each image in the image data set; Parameters and loss function; use the preprocessed image and the known image classification label as the input value of the convolutional neural network to start training the convolutional neural network; calculate the loss function according to the output of the convolutional neural network and the image label , and then carry out error backpropagation; in the process of error backpropagation, the gradient direction parameter optimization method is used to update the parameters in the training process of the convolutional neural network. After the end conditions are met, the iterative training is ended and the trained Convolutional neural network; based on the trained convolutional neural network, classify the images to be classified, and obtain the classification labels of the images to be classified. The present application has the advantages of fast image classification and strong stability.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image classification method and system based on a neural network optimized for gradient direction parameters. Background technique [0002] The statements in this section merely provide background related to the present disclosure and do not necessarily constitute prior art. [0003] In deep learning, multi-classification problems have always been a hot research area, and the most common multi-classification problem is image classification. When dealing with some image classification problems in deep learning, neural network models are required to be trained at any time. For example, in the face recognition access control system, when a new person enters the access control system, the face recognition neural network model must continuously train the face pictures of the newly added person. Therefore, speeding up the training speed of neural network models is very im...

AI Technical Summary

Problems solved by technology

But the disadvantage of this basic gradient descent method is that the learning rate is a hyperparameter, and there is almost no theoretical basis for its setting. Basically, the empirical value of the frequently used learning rate is obtained by experiment. The algorithm does not converge; if the learning rate is set to a small value, the algorithm converges very slowly, and even stops before reaching the optimum point. In the actual deep learning training, it takes a lot of time for parameter tuning

However, Newton's method has high requirements for the objective function to be optimized, and requires the Hessian matrix to be positive definite. At the same time, the calculation is too complicated, which makes the amount of calculation and storage in the process of optimizing the parameters of the neural network larger, which leads to the real In solving the actual image multi-classification problem, the Newton method, including the later improved quasi-Newton method, is not faster and more convenient than the gradient descent method

Newton's method has a fast convergence speed in theory, but the main reason why it is not as good as the gradient descent method in the process of image multi-classification is that more gradient information is used, which increases the complexity of actual calculation and increases the amount of calculation.

Images