Training method and device of hierarchical neural network for fluid simulation

The invention provides a training method and device of a hierarchical neural network for fluid simulation, and the method comprises the steps: obtaining multiple sample video frames in a sample video, and monitoring video frames corresponding to the multiple sample video frames in the sample video, obtaining optical flow information between the multiple sample video frames and the supervision video frame; inputting the multiple sample video frames into a to-be-trained hierarchical neural network, and determining background feature information and fluid feature information corresponding to the multiple sample video frames respectively; adjusting fluid feature information corresponding to each sample video frame based on the optical flow information corresponding to each sample video frame to obtain adjusted fluid feature information; and constructing a prediction video frame based on the background feature information and the adjustment fluid feature information, and training the to-be-trained hierarchical neu