Thijs van den Berg
Thijs van den Berg
Hi Corey, Thanks for your great blog post and sharing the code. I was wondering about the weights in the the cost functions: shouldn't the l2_losses in the _generative_loss_ function...
Hi taesung89, thanks for sharing the code! I have a question: I'm puzzled by the scale parameter in the get_normalized_weights function in the CouplingLayer: the routine first normalized the weights,...
Would it be possible to have a feature to set an EPSILON in the stationarity constraint? Like: 1 - sum(alpha) - sum(beta) -0.5*sum(gamma) - EPSILON >= 0 The reason it...