Model training method, electronic equipment and storage medium

Abstract

The invention relates to the technical field of machine learning, and particularly discloses a model training method, electronic equipment and a storage medium, and the method comprises the steps: obtaining a pre-trained super network model; determining a plurality of target sub-network models from a preset number of sub-network models of the super-network model; obtaining a plurality of mainstream network models based on open source data training; splicing each target sub-network model as a first backbone network with a first branch network to obtain a plurality of first spliced networks, and splicing each mainstream network model as a second backbone network with a second branch network to obtain a plurality of second spliced networks; performing fine tuning and testing on the plurality of first spliced networks and the plurality of second spliced networks to determine a target network model; and carrying out transfer learning on the target network model to obtain a required model, thereby realizing convenience and intelligence of model training, and improving user experience.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular, to a model training method, electronic device and storage medium. Background technique [0002] Neural Architecture Search (NAS) is one of the hotspots in the field of Automated Machine Learning (AutoML). By designing a cost-effective search method, a neural network with strong generalization ability and friendly hardware requirements can be automatically obtained. Therefore, a lot of manpower and material resources can be saved. The main working principle of NAS is to first define the search space, then find out the candidate network structures through the search strategy, evaluate them, and perform the next round of search according to the feedback until the target network structure is searched, and the automatic machine based on the target network structure is performed. Learn to get the model you need. [0003] However, the existing NAS search process i...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a model training method, electronic equipment and storage medium, aiming at solving the problem of waiting for a long time for neural network structure search, saving time and cost, and providing a more user-friendly experience

Images