Qi Mao

icon indicating an email [email protected]

icon company Communication University of China icon location CUC, Beijing, China icon location Associate Professor, Communication University of China，PhD from Peking University

Results 4 issues of Qi Mao

Questions about the attention map

2 comment

Hi, I am trying the AFHQ dataset of your model and find your model can preserve the background of the source image very well. I think it is thanks to...

Can not repeat the results on CelebA dataset.

2 comment

Hi, thanks for your great implementation. I run the model on CelebA dataset. However, when I test the model, I find if the categorical codes are fixed, different noise vectors...

How can I extend into other datasets such as MINIST?

Hi, thanks for sharing your codes! I notice your codes you embed the gaussian gird data in Bourgansampling directly when generating the gaussian grid. If I want to extend into...

Typos in gc_cycle_gan_model.py

Hi, thanks a lot for sharing your excellent work. I find there is a typo in gc_cycle_gan_model.py `` rec_B = self.netG_AB(fake_A) `` `` loss_cycle_B = self.criterionCycle(rec_B, self.real_B) * self.opt.lambda_AB ``...