ADAPTIVE SEARCH METHOD AND APPARATUS FOR NEURAL NETWORK

This application relates to the field of neural networks, and provides an adaptive search method and apparatus for a neural network, so that adaptive search for a neural network on a hardware platform can be implemented. The method includes: receiving a search condition set, where the search condition set includes target hardware platform information, network structure information of a source neural network, and one or more evaluation metrics, where the network structure information of the source neural network is used to represent the source neural network; performing a training process on a to-be-trained super network based on a training dataset, to obtain a trained super network, where the to-be-trained super network is obtained by extending a network structure of the source neural network; and performing a subnet search process on the trained super network based on the one or more evaluation metrics, to obtain network structure information of a target neural network, where the network structure information of the target neural network is used to represent the target neural network, and an evaluation result of the target neural network running on a target hardware platform is better than an evaluation result of the source neural network running on the target hardware platform.