Force float64

[mhuen]

Use float64 in crucial code parts. Changes include:

• Loss module can now fully use its own float precision
• basis functions now have an optional dtype parameter that will cast all inputs to this dtype
• Force pdf and cdf evaluation in cascade and inf_track model in float64 and then revert back to model float precision
• change latent parameter scaling/boundaries back to elu function and reduce lower bound for sigma and r by one order of magnitude