pyro

A quick search for mixture distributions in numpyro only turns up examples using Categorical in conjunction with an array of distributions. Since sampling from discrete distributions is not always desirable, I have implemented a quick general purpose mixture distribution with continuous log probability.

class Mixture(Distribution):
    arg_constraints = {}

    def __init__(self

See wikipedia table for example patterns: https://en.wikipedia.org/wiki/List_of_integrals_of_Gaussian_functions

Currently, all the VED/VAE models work only with a single channel data (e.g. grayscale images but not color images). The extension to multiple channels should be pretty straightforward if there is a use case.