Optimization method of neural network model, data processing method and device

Abstract

The present disclosure provides a neural network model optimization method, a data processing method and device, the neural network model comprises a plurality of operators, the optimization method comprises: selecting a target algorithm corresponding to each candidate data format from at least one candidate algorithm corresponding to each candidate data format in a plurality of candidate data formats; determining a search path corresponding to each operator according to a target algorithm corresponding to at least one data format supported by each operator; wherein the plurality of candidate data formats comprise the at least one data format; searching based on the search path corresponding to each operator in the plurality of operators to obtain an optimized neural network model. The neural network model optimization method narrows down the search space by determining the target algorithm for each data format, and then searches within the search space to achieve the purpose of more efficient and lower cost optimization of the neural network model.

Images