gouchaonijiao

about the comparison experiments

2

Hello! I am curious about the details of the comparison experiments , since the inputs of HumanGAN and other models are not human parsing and clothes texture attributes. Looking forward...

about the size of tgt_pose when inference

7

Hello! Your work is very impressive,but I wonder why the image and tgt_tensor are scaled to 256*256? And how I get other size of tgt_tensor like (256,512). Wish your reply!

About the tgt_pose when inference

8

Hello! Thanks for your amazing work! I want to know that how I make more "data/deepfashion_256x256/target_pose/*.npy" ?

can you teach me how the"frozen_out" work? thanks!

2

frozen_out = th.cat([model_output.detach(), model_var_values], dim=1) terms["vb"] = self._vb_terms_bpd( model=lambda *args, r=frozen_out: r, x_start=x_start, x_t=x_t, t=t, clip_denoised=False, )["output"]