查看文章

In one aspect, the present disclosure relates to a method for automatically scaling a neural network including: receiving a neural network model; allocating a plurality of processing nodes for the neural network model, the number of allocated processing nodes determined based on an analysis of the neural network model; distributing training of the neural network model across the allocated processing nodes; receiving load information from the allocated processing nodes, the load information associated with the training of the neural network model; and adjusting the number of allocated processing nodes based on the load information.