jbm

It seems I'm mistaken about the error here. I tried doing some reshaping to replace the BatchNorm2d with a BatchNorm1d, but I still get the error: `Error while converting op...

@Jazzpirate This is awesome! The only thing that's a bit unfortunate (though probably operator error) is that it only seems to run on cpu for me. Is there a way...

ah... wait... `batch_size=32` seems to get it running. What would be the solution to allowing a larger batch size?

Oh, okay, seems like a false alarm—rebooting my ubuntu box seems to have solved the problem (also learned about clearing GPU memory in the meantime)!

I'm actually still on cuda 8.0.61, with pytorch 0.3.1—I haven't run this for a while. But for me the solution was just a reboot and then adjusting the batch_size to...

Yes, I was curious about the idea of a latent direction that basically finds similarities between classes, so it could potentially shift across multiple classes in an interpretable way (e.g.,...

Unfortunately I gave up (at least for now).

Hi @jmoso13, I'm curious about this PR. Beyond taking inspiration from the refinements in SoundStream and EnCodec, are there any specific improvements you've noticed with this addition? I'm intuitively guessing...

Yeah, I'm having the same issue. I can see that `datamodule` isn't in `config.yaml`, so I guess it's just broken... Not a huge deal to write a new training script.

Okay, running now. Thanks! I'm curious; since I'm not familiar with Hydra or OmegaConf (yet) I'm not really clear what I'm training on when running `base_test.yaml`. Is this training on...