Image processing method, device and equipment and readable storage medium

Abstract

The invention discloses an image processing method, device and equipment, and a readable storage medium. The method comprises the steps of obtaining a target image; inputting the target image into thequantized target deep neural network model for classification/detection to obtain an output result; processing the target image according to a strategy corresponding to the output result, wherein theprocess of obtaining the target deep neural network model through quantification comprises the steps of obtaining a floating point type deep neural network model obtained through pre-training; extracting weight features of the deep neural network model; determining a quantization strategy by utilizing the weight characteristics; and quantifying the deep neural network model according to a quantification strategy to obtain a target deep neural network model. According to the method, in the process of obtaining the target deep neural network model in a quantified mode, occupied resources are reduced, consumed time is shortened, and meanwhile model performance can be guaranteed, so that image classification/detection performance is guaranteed, and image classification processing performancecan be further improved.

Description

technical field [0001] The present invention relates to the field of computer application technology, in particular to an image processing method, device, equipment and readable storage medium. Background technique [0002] Processing images based on image classification / detection can improve the pertinence of image processing and make the processing results more in line with expectations. [0003] However, in practical applications, deep neural network models for image classification / detection often have a large model size and high hardware cost requirements. At the same time, in peripheral applications, terminal devices or edge devices generally have low computing power, and memory and power consumption are also limited. Therefore, in order to truly implement the deployment of the deep neural network model, it is very necessary to make the model smaller to make its reasoning faster and lower power consumption while ensuring the accuracy of the model remains unchanged. In...

AI Technical Summary

Problems solved by technology

[0004] At present, although the quantization of the deep neural network model can make the model smaller and reduce the hardware requirements, different quantization methods also make the quantization process too time-consuming, or the performance of the quantized model is affected.

Makes it difficult to meet the needs of image classification / detection accuracy

Images