Data processing method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a data processing method and device, computer equipment and a storage medium. When an optimizable structure exists in a neural network model, optimization forthe neural network model can be realized by executing at least one optimization operation in multiple optimization operations on the neural network model, and the overall performance of the neural network model is improved. When a request of a machine learning processing task is received, redundant calculation can be reduced by calling the optimized neural network model, and then resource consumption of computer equipment is reduced.

Description

technical field [0001] The present application relates to the technical field of information processing, and in particular to a data processing method, device, computer equipment and storage medium. Background technique [0002] Neural network is an algorithmic mathematical model that imitates the behavior characteristics of animal neural networks and performs distributed parallel information processing. This network is composed of a large number of nodes (or neurons) connected to each other. The connection relationship uses input data and weights to generate output data to simulate the information processing process of the human brain to process information and generate results after pattern recognition. [0003] Currently, when designing a neural network model, algorithm designers often introduce "glue" operators into the neural network model for the purpose of neat and concise description of the neural network model. Here, the "glue" operator means that the operator itse...

AI Technical Summary

Problems solved by technology

However, the introduction and combination of unreasonable "glue" operators can lead to the addition of some unnecessary and unreasonable memory access behaviors in the execution process of the neural network model on the higher-level computing layer, which affects artificial intelligence. The intelligent processor optimizes the hardware structure and instruction design of the calculation part of the neural network model to improve the excellent performance, which reduces the overall performance of the neural network model.

Then, when the computer equipment is running the above-mentioned neural network model containing the "glue" operator that can be optimized, this will undoubtedly increase the resource consumption of the computer equipment.

Images