Image semantic segmentation model optimization method and device, electronic equipment and storage medium

The invention provides an image semantic segmentation model optimization method and device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to computer vision, image recognition and deep learning technologies, and can be particularly applied to smart cities and intelligent traffic scenes. The technical problem that the accuracy of a model obtained through pseudo tag training is poor in the prior art is at least solved. According to the specific implementation scheme, multiple target images are obtained, and the multiple target images are obtained by performing different data enhancement processing on original images; the multiple target images are input into the multiple models, multiple recognition results of the target pixel points are obtained, the positions of the target pixel points in the multiple target images are the same, and the multiple recognition results are used for representing the types of the target pixel points; determining