NEURAL NETWORK MODEL UPDATE METHOD, AND IMAGE PROCESSING METHOD AND DEVICE

摘要

The present application discloses a neural network model update method, and an image processing method and device in the field of artificial intelligence. The neural network model updating method comprises: acquiring a structure of a neural network model, and a related parameter of the neural network model; training the neural network model on the basis of the related parameter of the neural network model to acquire a trained neural network model; and if an evaluation result of the trained neural network model does not meet a preconfigured condition, updating at least two items in the related parameter and the structure of the neural network model until an evaluation result of the updated neural network model meets the preconfigured condition and/or the number of updates reaches a preconfigured value. The method of the present application improves update efficiency of a neural network model, and obtains a structure and/or a related parameter of a neural network model having improved performance.