A Deep Neural Network Method Based on Information Lossless Pooling

Abstract

The invention relates to a deep convolutional neural network method based on information lossless pooling, which is used for image classification, comprising the following steps: collecting various types of images, and marking the image categories as image label information; dividing the image set, dividing The collected images are divided into training set, verification set and test set; design a convolutional neural network structure based on information lossless pooling, including the number of convolutional layers used and the number of information lossless pooling layers, and design the convolutional layer The number of filters, design information lossless pooling layer Gaussian smoothing filter parameters, pooling window size and convolution filter structure for feature fusion, design the number of network training loop iterations and network final convergence conditions, and initialize Network parameters; batches of training data are input into the network for calculation and training.

Description

technical field [0001] The invention relates to a method for high-performance picture classification and object recognition in the field of computer vision, in particular to a method for carrying out picture classification and object recognition using a deep learning method. Background technique [0002] In recent years, deep learning technology has been widely used in multiple tasks such as image classification, semantic segmentation and object detection, and automatic driving in the field of computer vision. As an important implementation method in deep learning technology, deep convolutional neural network has achieved remarkable results in many tasks. [0003] Deep convolutional neural networks are often composed of multi-layer convolutional layers and pooling layers. The convolutional layer contains filter parameters for feature extraction, and the pooling layer is used to maintain the translation invariance of the neural network and reduce the impact of data disturbanc...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to overcome the problems of feature information loss and high complexity of pooling operations in the existing deep neural network pooling layer operation, and propose a deep neural network method based on information lossless pooling, which can effectively maintain The feature information of all feature maps in the pooling process further improves the performance of deep neural networks for various computer vision tasks

Images