Method, electronic device and computer program product for deploying a machine learning model

Abstract

Embodiments of the present disclosure relate to a method, an electronic device and a computer program product for deploying a machine learning model. The method comprises: obtaining a machine learning model in an open neural network exchange format; converting the machine learning model into an intermediate representation using a multi-level intermediate representation method; and deploying, using the intermediate representation, a computation associated with the machine learning model to at least one computing device. Using the technical solution of the present disclosure, any machine learning model can be deployed, machine learning models can be deployed to humans and computing devices, and more intensive machine learning tasks can be deployed to computing devices with higher performance, thereby enabling convenient and reasonable machine learning model deployment, improving the efficiency and effectiveness of machine learning model deployment, and helping to improve the computational efficiency of machine learning models, thereby improving the user experience associated with machine learning models.

Images