Torch. Distributions. Normal

Pytorch Normal distribution provided , Official documents
How it was created

>>> m = Normal(torch.tensor([0.0]), torch.tensor([1.0]))
>>> m.sample()  #  Generate the data , Biography shape Parameters 
        tensor([ 0.1046])

Interface log_prob(self, value)

return value Probabilistic log value , The normal distribution formula is
$$f(x)=\frac{1}{\sqrt{2\pi }\sigma }exp(-\frac{(x-\mu {)}^2}{2{\sigma }^2})$$
The calculation formula of the function is ：
$$log(f(x))=-log(\sqrt{2\pi })-log(\sigma )-\frac{(x-\mu {)}^2}{2{\sigma }^2}$$

Interface def entropy(self)

Return value formula
$$\frac{1}{2}+\frac{2\pi }{2}+log(\sigma )$$
It looks like the normal distribution formula log value , But I don't know why $\frac{1}{2}$