Hello,

I am quite new in the field and in the use TF, so I probably ask a rather easy question, but I was wandering

how I can implement this transformation as a Bijector (all the “w” and “alpha” are >0)

$$T(z_i) = w_{i0} + \sum_{k=1}^K w_{ik}\rho(\alpha_{ik} z_i + \beta_{ik})$$

this is just to illustrate an how-to, for instance K=2 and z_i is either a 1-scalar feature or a 2-scalar features.

Thanks for your help.

- import tensorflow as tf import tensorflow_probability as tfp
**tfd = tfp.distributions**tfb = tfp.bijectors base_distribution = tfd.Normal (loc=0, scale=1.5) x = base_distribution.sample (10) # Sample 10 times, to get fixed values # Define the distribution for the parameter of the bijector scale_distribution = tfd.Uniform (low=2/3-0.5, high=2/3+0.5) # This is how I wish it was, but fails bijector = tfb.Scale (scale=scale_distribution) # ValueError: TypeError: object of type ‘Uniform’ has no len ()

(*Removed by moderator*)