Model parameter processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a model parameter processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining the sizes of different model parameter groups of a neural network model stored in a server and the data sizes corresponding to the model parameter groups; according to the size of the storage space locally used for storing the model parameter groups and the size of the obtained model parameter groups, calculating the number of the model parameter groups capable of being stored in the storage space as the number of the parameter groups; and according to the data size corresponding to each model parameter group, obtaining the parameter groupnumber of themodel parameter groups from the server. By applying the scheme provided by the embodiment of the invention to process the model parameters, the requirement of the storage model parameter group in theequipment on the storage space can be reduced.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a model parameter processing method, device, electronic equipment and storage medium. Background technique [0002] The neural network model is described by various model parameters, and these model parameters form different model parameter groups when they take different values. Each model parameter group corresponds to a data size, that is, when the neural network model performs data processing based on each model parameter group, when processing data whose data size is consistent with the data size corresponding to the model parameter group, it can be obtained Better processing effect. [0003] For example, when the above data is an image, the data size may include: resolution 720×480, resolution 1920×1080, etc. Since the above two resolutions are different, two different model parameter groups are required to be compared with the above two correspond...

AI Technical Summary

Problems solved by technology

However, the storage space occupied by each model parameter group is often large, and the storage space occupied by multiple model parameter groups is even larger

For this reason, due to the large storage space occupied by a variety of different model parameter groups, it is difficult to use neural network models for data processing on devices with limited storage space such as mobile phones, tablet computers, and image acquisition equipment.

Images