Image shape transformation method based on generative adversarial network

The invention discloses an image shape transformation method based on a generative adversarial network. The method comprises the following steps: generating a segmentation mask of an image to be transformed; constructing a generator and a discriminator, and constructing a generative adversarial network through the generator and the discriminator; constructing a loss function, and training the generative adversarial network by a gradient descent method according to the loss function; and inputting the segmentation mask of the image to be transformed into the trained generative adversarial network to obtain a graphic shape transformation result. The method is low in complexity and high in image conversion efficiency, can efficiently process a specific image in the picture to carry out graph conversion with large shape difference, can be applied to the fields of animation production, poster design and the like, can enhance the trueness of graph conversion, and can also reduce the labor cost and the workload. 本发明