Question about variance calculation in sampling step

[HIT-LiuChen]

In Diffusion.py line 66, posterior_var is calculated. Why do you use torch.cat([self.posterior_var[1:2], self.betas[1:]]) in line 77 to extract variance instead of posterior_var.

    def p_mean_variance(self, x_t, t):
        # below: only log_variance is used in the KL computations
        var = torch.cat([self.posterior_var[1:2], self.betas[1:]])    # i think var should be equal to self.posterior_var
        var = extract(var, t, x_t.shape)

        eps = self.model(x_t, t)
        xt_prev_mean = self.predict_xt_prev_mean_from_eps(x_t, t, eps=eps)

        return xt_prev_mean, var

[ljw919]

I have the same doubt, what's the reason for doing this ?

[kache1995]

俺也有这个疑问，方差不是应该是self.posterior_var吗

[tsWen0309]

Have you solved the problem? Can you fill me in?

[MetaInsight7]

@zoubohao Could you answer this issue? Thank you!

[chenchen278]

In the paper DDPM, it seems that var is equal to posterior_var or betas. And I don't know why they were concatenated here?