Closed LGYoung closed 3 years ago
At the time of research, I do split train-test sets, train on training set then test on the test set. But recent research in GANs does not really need that, since the train/test distribution difference is really small, and the FID does not have significant differences.
Hi, I also try to test your model on my costume dataset. One question about your testing procedure: Do you split the CelebA( or CelebA-64*64) dataset for training and testing, and precalculate the fid-stat on the testing part? Or do you pre-calculate the fid-stat on the whole dataset, train the model using the whole dataset, and compare the statistics of fake samples with the pre-calculated fid-stat?