aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
Executing the code for the model in the Challenger Space Shuttle Disaster example, it returns an AttributeError, roughly "tfp.bijectors has no attribute AffineScalar".
After an unusually long search in the internet, I found that, as per this source (https://github.com/tensorflow/probability/releases), this attribute is indeed deprecated. The release said to use tfp.Shift(shift) or tfp.Scale(scale), instead. Since the code called for a multiplying factor, I substituted the line for tp.bijectors.Scale(100.).
It worked fine.
Executing the code for the model in the Challenger Space Shuttle Disaster example, it returns an AttributeError, roughly "tfp.bijectors has no attribute AffineScalar". After an unusually long search in the internet, I found that, as per this source (https://github.com/tensorflow/probability/releases), this attribute is indeed deprecated. The release said to use tfp.Shift(shift) or tfp.Scale(scale), instead. Since the code called for a multiplying factor, I substituted the line for tp.bijectors.Scale(100.). It worked fine.