How could I add extra pre-processing operations only to the input of Discriminator?

[HJLYU0519]

I made some changes to the Discriminator. And I want to add some extra pre-processing operations only to the input of Discriminator. What should I change? And I think there are no preprocessing operations. my reason is this: in data/init.py 75 self.dataloader = torch.utils.data.DataLoader( 76 self.dataset, 77 batch_size=opt.batch_size, 78 shuffle=not opt.serial_batches, 79 num_workers=int(opt.num_threads))

Should I establish another dataloader only for Discriminator? Many thanks for your kind help

[junyanz]

That is one possibility. You can also manually add some preprocessing code before you call the netD.forward. Like here.