Method p_mean_variance

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which takes a signal and a batch of timesteps as input. :param x: the [N x C x ...] tensor at time t. :param t: a 1-D Tenso

(
        self, model, x, t, clip_denoised=True, denoised_fn=None, model_kwargs=None
    )