Steven Atkinson

Thanks for the input so far. I haven't had the time to try with `jax.remat` yet but found that implementing the function above using a pair of `jax.vmap`s like the...

On one hand, I'm open to loading different audio file formats. At the bottom, the audio loading [comes from `wavio`](https://github.com/sdatkinson/neural-amp-modeler/blob/ae8697914a0ce3f32a4e9e3332d16c12451e5d86/nam/data.py#L82). First step with this would be to suggest to me...

That's how it works currently 👍🏻 --- Coming back to this, I'm not going to implement it because I don't think that it helps the core aim of this repo,...

Apologies for the very long wait on this one. As you're already aware, .nam files are readable as JSON files, and I'm happy to keep it that way since it's...

@vossenv's suggestion is what I'd usually recommend to someone who knows their way around Python & its environment management tools, but I'm going to assume that this is the only...

One more potential issue: the [current advice](https://pytorch.org/get-started/locally/) for installing PyTorch with CUDA support using conda for windows appears to be (after removing torchvision and torchaudio, which shouldn't be necessary): ```...

[Edit: this now on my Windows 11 desktop. Windows 11 Pro, Version 23H2. Seems to be up to date.] I just did a fresh install of Anaconda 2024.02. I clicked...

Closing since no reply; assuming this fixes it

I like this idea. However, your PR does unfortunately introduce a lot of issues that need to get addressed before I can merge it. I'll need to find some time...

@Eraz1997 on second thought, if you can grab those changes before Thursday you'll probably get to it before me :)