is it a bug in HyperbolicMLR?

[chenkq7]

Thanks a lot for sharing your repo. I am new to hyperbolic neural networks, and I learned a lot from your repo.
While i am reading the code of examples/mnist.py, i am curious about why ToPoincare is only applied for x which is calculated by a neural network, whereas, ToPoincare is not applied for p_val in HyperbolicMLR.

hyperbolic-image-embeddings/hyptorch/nn.py

Line 30 in 6633edb

p_vals_poincare = pmath.expmap0(self.p_vals, c=c)

consider that they are both need a expmap0 to map them from $R^2$ to $D^2$, won't p_val get a wrong gradient?