About Dirichlet distribution

[mountains-high]

Hi~
Thank you for providing the great work!

While running, I got the following error message:

ValueError: Expected parameter concentration (Tensor of shape (10,)) of distribution Dirichlet(concentration: torch.Size([10])) to satisfy the constraint IndependentConstraint(GreaterThan(lower_bound=0.0), 1), but found invalid values:
tensor([1.0000, 0.4503, 0.4462, 0.2881, 0.3598, 0.0000, 0.3248, 0.3540, 0.5790,
        0.4990], grad_fn=<SliceBackward0>)

Usage:

diri_list = []
    for i in range(labels):
        m = Dirichlet((normalized_cormat[i,:]))
        diri_list.append(m)

Could you help me to solve this issue, please?
Thank you

And I think these lines are unnecessary https://github.com/Intelligent-Computing-Lab-Yale/PrivateSNN/blob/074f7ad9b4ab8aa351163076d068f1d0ca275689/image_gen_function.py#L166 How do you think?