During training, a dataloder is created that holds datasets of the source domain and the target domain, and then the images of the source domain and the target domain are read respectively.
I try to reproduce your racs.
I find your code use mmseg. and then I meet the problem. I don't know how to load the source image and target image resepectly.
During training, a dataloder is created that holds datasets of the source domain and the target domain, and then the images of the source domain and the target domain are read respectively.
I try to reproduce your racs. I find your code use mmseg. and then I meet the problem. I don't know how to load the source image and target image resepectly.