Checkerboard masking in RealNVP

[Donglin-Wang2]

Hi,

Since the CouplingTransform class in nflows.transforms.coupling module only supports a 1-d mask that splits data along the channel dimension, I am wondering how I would go about implementing the alternating checkerboard mask in the RealNVP paper? Should I used the MaskedAffineAutoregressiveTransform in the nflows.transforms.autoregressive instead? Or are there some other methods or classes that I am not aware of?

Also, thank you so much for providing such a clean implementation of flow models in PyTorch!

Sincerely, Donglin Wang

[arturbekasov]

Hey Donglin. Nope, unfortunately the checkerboard masking isn't implemented. I'll keep this issue around in case you (or someone else) want to implement it. Cheers, Artur

[arturbekasov]

We do have a RealNVP implementation with 1D checkerboard masking, though: https://github.com/bayesiains/nflows/blob/master/nflows/flows/realnvp.py#L17