Classification detection network model construction method

Abstract

The invention discloses a classification detection network model construction method, which comprises the steps of obtaining a training sample of a to-be-classified object image, establishing a training model data set, and inputting the training model data set into a first convolutional network model for training to obtain a weight file; inputting the weight file into a second convolutional network model to obtain a feature map and an original image corresponding to each layer of convolutional network; inputting the feature map corresponding to each layer of convolutional network and the original image into an image quality evaluation algorithm to obtain an evaluation result; selecting an appropriate convolution operation step length corresponding to each layer of network in the first convolution network model according to the evaluation result, increasing the number of convolution kernels, and forming new convolution network parameters; and updating the first convolutional network model by using the new convolutional network parameters to obtain a classification network model. The requirements of flexible detection and intelligent detection are met, and the detection cost and thedetection complexity are reduced.

Description

Technical field [0001] The invention belongs to the technical field of classification detection models, and relates to a method for constructing a classification detection network model. Background technique [0002] With the development of big data and computer hardware, neural networks have risen again. Deep learning, artificial intelligence, big data, Internet of Things and other technologies have begun to develop by leaps and bounds. Driven by the development of computer technology, the manufacturing industry has begun to move from traditional mechanized production to tasks. The heavy rigid manufacturing method is gradually transformed into an automated, intelligent and flexible intelligent manufacturing method in which machines replace manual labor. Artificial intelligence is not only limited to the computer field, but has become a field with many practical applications and active research topics. Deep learning is the study of how computers simulate human learning behaviors...

AI Technical Summary

Problems solved by technology

However, the integration of deep learning and industrial technology has not really achieved flexible detection, and there is no classification network model that can automatically adjust for different detection objects.

Images