Method for coding photonic crystal through deep neural network based on self-attention

The invention discloses a method for coding a photonic crystal based on a self-attention deep neural network, and provides a POViT model, and the POViT model is applied to the coded photonic crystal. The method comprises the following steps: acquiring a geometric structure parameter image of the photonic crystal; the photonic crystal is provided with a plurality of air holes, and each pixel of a geometric structure parameter image of the photonic crystal comprises the position and the radius of the air hole; carrying out dimension remodeling on the geometric structure parameter image to obtain a plurality of patch images; inputting the patch image into an embedding module and a position coding module to obtain a symbol sequence; inputting the symbol sequence into a transform coding module to obtain a coding feature; and inputting the coding features into a full connection layer module to obtain a quality factor Q and a mode volume V. The POViT applies a self-attention Transform model to the field of photoelec