k value in the kl distance equation of 3D data in 3d_autoencoderkl_tutorial.py

[minghuix98]

If the dimension k=3 for three dimensional data, then the following -1 should be -3/2? line 259: kl_loss = 0.5 * torch.sum(z_mu.pow(2) + z_sigma.pow(2) - torch.log(z_sigma.pow(2)) - 1, dim=[1, 2, 3, 4])