David Nicholson

Hi @dimbleby you are right. I raised several points out of frustration but that just distracted from the question raised by the person who opened the issue, adding noise to...

I'm not a maintainer, but ... not sure if this is a bug: https://docs.xarray.dev/en/stable/getting-started-guide/faq.html#what-is-your-approach-to-metadata > An implication of this choice is that we do not propagate attrs through most operations...

Re-opening this because we haven't added datasets yet

Also because after discussion with @yardencsGitHub it's clear that I have made a mistake in my implementation and need to do further work on this Leaving the initial implementation in...

I think we can still add a TCN model, e.g. from here https://github.com/vocalpy/Nicholson-Cohen-SfN-2023-poster We just shouldn't claim to perfectly replicate DAS

🙌 awesome, thank you @marisbasha! This looks great. I had a quick look and can see you made the changes we discussed. I will review in the next couple of...

> @NickleDave I have github desktop, so its automatically synced, I can see it from the app. Excellent 🤔 maybe I should be using GitHub desktop > Let me know...

@all-contributors add @marisbasha for code

@marisbasha following up on our discussion today: let's use the TorchMetrics.KLDivergence class. But just for future reference, as far as I can tell it would be equivalent use `torch.nn.KLDivergence` (the...

🚀 great, thank you @marisbasha -- I will get back to this this week. (I need to get [this branch](https://github.com/vocalpy/vak/tree/minimize-frame-classification-dataset-size-fix-%23717) merged in so I can re-start experiments and deal with...