David Nicholson

Hi @marisbasha I made some progress on this but I get an error when I start training -- if you have a chance before I do to test with the...

Thank you @marisbasha for figuring out where the error is coming from. Sorry for not replying sooner; I was under a deadline, and in the middle of changing jobs. I...

Hi @marisbasha, sorry I wasn't able to look at this sooner. Now that I have, I think you are right -- we should give the network an `input_shape` parameter and...

Hi @marisbasha, getting closer on this. I'm going to leave two comments. The first summarizes changes I made; please let me know what you think, especially if you spot any...

Okay, comment two: what do we need to change I have a branch here with a couple of notebooks in the project root: https://github.com/vocalpy/vak/tree/test-ava-in-notebook * In `test-vae` I just run...

Hi @marisbasha I thought about this some more and I feel like it's best to replicate the AVA pre-processing pipeline. I'm happy to do that. It doesn't have to be...

Hi @marisbasha hope you're having a good holiday -- just letting you know I didn't forget about this. It's at the top of my to-do list to finish up next...

Hey @marisbasha thanks for reaching back out and picking this up again. Just writing notes on next steps from our call today: - [ ] run train and understand why...

I'm noticing this because I have old configs where train_set_durs and replicates are specified in the LEARNCURVE section -- these options in that section should cause an error? But they...

- factor `extract` out of `features` - would make sense to have `features` as a namespace, with a matching entry point so that user-defined features could be installed as plug-ins...