Method p_sample

usr/diff/shallow_diffusion_tts.py:278–284

(self, x, t, cond, clip_denoised=True, repeat_noise=False)

    @torch.no_grad()
    def p_sample(self, x, t, cond, clip_denoised=True, repeat_noise=False):
        b, *_, device = *x.shape, x.device
        model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, cond=cond, clip_denoised=clip_denoised)
        noise = noise_like(x.shape, device, repeat_noise)
        # no noise when t == 0
        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
        return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise

    def q_sample(self, x_start, t, noise=None):
        noise = default(noise, lambda: torch.randn_like(x_start))