Image processing model searching method and device, image processing method and device and storage medium

Abstract

The invention relates to an image processing model searching method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring an image data set and an image processing network search space; selecting a current sub-network from the image processing network search space to obtain a current image processing model; inputting the training data set into the current image processing model and the reference image processing model for knowledge distillation to obtain a current training image processing model; evaluating the current training image processing model based on the verification data set to obtain an image processing evaluation result, and updating the current training image processing model based on the image processing evaluation result to obtain a target training image processing model; and updating a sub-network in the image processing network search space based on the target training image processing model, and performing loop iteration until the search is completed, selecting a target sub-network from the image processing network search space, and obtaining a target image processing model. By adopting the method, the search accuracy can be improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to an image processing model search, image processing method, device, computer equipment and storage medium. Background technique [0002] With the development of artificial intelligence technology, a neural network architecture search technology has emerged, which can reduce the time cost of manually designing a network. Currently, during the image processing model training process, the neural network architecture search technology can also be used for neural network architecture search. For example, the neural network architecture of the image processing model is searched through a random search strategy. However, the accuracy of the neural network architecture obtained by searching through the random search strategy is low, resulting in low image processing performance of the image processing model. Contents of the invention [0003] Based on this, it is necessary ...

AI Technical Summary

Problems solved by technology

For example, the neural network architecture of the image processing model is searched through the random search strategy. However, the accuracy of the neural network architecture obtained by searching through the random search strategy is low, resulting in low image processing performance of the image processing model.

Images