Discrete normalizing flow attemp

gistfile1.jl

using Distributions


function sample_prior()
    return rand(Beta(1, 1))
end

function generate_data()
    θ = sample_prior()
    y = rand(Binomial(10, θ))
    return [θ,y] 
end

# train using samples from joint distribution x,y ~ p(x,y) where x=[μ, σ] -> y = N(μ, σ)
# rows: μ, σ, y
num_params = 1; num_obs = 1; n_train = 10000
training_data = mapreduce(x -> generate_data(), hcat, 1:n_train);

############ train some data
X_train = reshape(training_data[1:num_params,:], (1,1,num_params,:));
Y_train = reshape(training_data[(num_params+1):end,:], (1,1,num_obs,:));

n_epochs   = 2
batch_size = 200
n_batches = div(n_train, batch_size)

# make conditional normalizing flow
using InvertibleNetworks, LinearAlgebra, Flux

L = 3 # RealNVP multiscale layers
K = 4 # Coupling layers per scale
n_hidden = 32 # Hidden channels in coupling layers' neural network
G = NetworkConditionalGlow(num_params, num_obs, n_hidden,  L, K;);