Neural network model deployment method, prediction method and related equipment

Abstract

The embodiment of the invention provides a neural network model deployment method, a prediction method and related equipment, and the method comprises the steps: reading an initial neural network model, and obtaining the layer definition of each network layer of the initial neural network model and the operation parameters of each network layer; according to the layer definitions of all the network layers, realizing corresponding target network layers of all the network layers in the terminal equipment by the Layer class, so that all the target network layers inherit the Layer class; connecting each target network layer by using a Net class; converting the operation parameter of each network layer into a predetermined format to obtain a target operation parameter of each network layer; andaccording to the target operation parameters of the network layers, loading the corresponding target operation parameters in the corresponding target network layers of the network layers to obtain atarget neural network model deployed in the terminal device. According to the embodiment of the invention, deployment from the neural network model to the terminal equipment can be realized, and the deployment universality from the neural network model to the terminal equipment is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a neural network model deployment method, a prediction method and related equipment. Background technique [0002] Neural network, especially convolutional neural network (CNN, Convolutional Neural Network), as an important branch of deep learning, has become a research hotspot in the fields of speech analysis and image recognition. The practical application of neural network is generally divided into neural network model training and neural network model prediction. [0003] Neural network model training can be understood as learning and adjusting the parameters of the neural network based on a large number of sample data to obtain the neural network model of the required function; neural network model prediction can be understood as being based on the trained neural network model. Predict the input data to perform calculations, determine the prediction results (such as...

AI Technical Summary

Problems solved by technology

[0004] Generally speaking, neural network model training is carried out on the server and deployed on the server, which makes the prediction of the neural network model need to be carried out jointly by the terminal device and the server. For example, after the neural network model is trained, the terminal device obtains the prediction input data and Submitted to the server, the neural network model is predicted by the neural network model deployed on the server, which undoubtedly leads to certain difficulties in meeting the speed and real-time requirements of the neural network model prediction; The speed and real-time performance of the neural network model prediction provide the basis, which has become a problem that those skilled in the art need to consider

Images