NEURAL NETWORK DATA PROCESSING METHOD AND APPARATUS

Disclosed are a neural network data processing method and apparatus, relating to the field of artificial intelligence. The method comprises: according to a data volume of input data, a first feature of an internal memory inside a chip for running a neural network, and a second feature of a plurality of layers in the neural network, dynamically segmenting the input data, so as to set different batch sizes for the layers in the neural network. By means of setting a reasonable batch size for each layer in a neural network, an internal memory can be fully used to store interlayer data of the neural network during a neural network reasoning process, such that the utilization rate of the internal memory is improved, and the computing efficiency of hardware for running the neural network is ensured. L'invention concerne un procédé et appareil de traitement de données en réseau neuronal, se rapportant au domaine de l'intelligence artificielle. Le procédé comporte l'étape consistant: selon un volume de données de donn