唐孟

noise = default(noise, lambda: torch.randn_like(y_0)) y_noisy = self.q_sample( y_0=y_0, t=t, noise=noise) if mask is not None: noise_hat = self.denoise_fn(torch.cat([y_cond, y_noisy*mask+(1.-mask)*y_0], dim=1), t) loss = self.loss_fn(mask*noise, mask*noise_hat) else: noise_hat = self.denoise_fn(torch.cat([y_cond,...

Some of the results are full of noise.

10

Some of the results are full of noise. And there are few results successful to me. Maybe like this.  

Thanks for your nice work. I want to know the ssim and psnr value is mean±std. That mean one model run on one model only once? How does the p...