Data processing method and device based on transformation neural network, and medium

The embodiment of the invention provides a data processing method and device based on a transformation neural network and a medium, and the method is applied to a normalization module in the transformation neural network, and specifically comprises the steps: receiving a data matrix corresponding to a first data sequence; the transformation neural network is used for converting the first data sequence into a second data sequence; determining a first mean value parameter value corresponding to the data matrix; dividing the data matrix by the first mean parameter value to obtain a first intermediate matrix; performing affine transformation on the first intermediate matrix, and determining a normalized matrix corresponding to the data matrix according to an affine transformation result; and outputting the normalized matrix. Wherein the first data sequence is an image sequence, and the second data sequence is an image category sequence. According to the embodiment of the invention, the stability of the normalizat