How to learn y condition? about glow-pytorch HOT 4 OPEN

I added priors in every blocks because of split2d_prior in this lines: https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L551

I think easy way to use class conditions is use class labels as an additional inputs is NN of affine coupling layers:

from glow-pytorch.

Following @rosinality's advice, it works with label conditioning on MNIST.

I added a label conditioning to the affine coupling layers instead of the prior (this is good because the net in this layer doesn't interfere with the invertibility of the model).

I also added a classifier working on the forward pass of the model. This classifies the final latent vector output and the logits are compared with the labels in a loss term added to the total original loss.

Thanks again @rosinality :)

(these are some samples with a shallow model with minimal filters in the coupling net)

from glow-pytorch.

@hologerry Can you share the codes about y condition? Thank you very much！

from glow-pytorch.

@hologerry Can you share the codes about y condition? Thank you very much！

Hi, do you solve the problem? Can you share the codes about y condition? Thank you very much！

from glow-pytorch.