Tim Sainburg

> So as far as I can tell this will just sit alongside the existing Keras3 implementation (which should now support a pytorch backed) just fine as an extra pytorch...

@turian I think this is out of the scope of the umap python library, but I give an example of how to build your own graph and iterator here: https://colab.research.google.com/drive/1WkXVZ5pnMrm17m0YgmtoNjM_XHdnE5Vp?usp=sharing...

Thanks for pointing this out. I have some updates that I'm working on related to upgrading keras to 3.0 that I can incorporate this into.

Sounds like a good idea. On Thu, May 2, 2024 at 5:37 PM Brad Nelson ***@***.***> wrote: > Parametric UMAP stores multiple copies of the full input data, but these...

I believe _history has been moved in a recent update to tensorflow / keras, try inspecting the ParametricUMAP object or downgrading keras to the version from around 2020. Alternatively you...

I suppose it could if you wanted it to

Hey. Not sure what you mean. If you email I can send you the final compiled version of the latex document for this paper (too big to upload here) downloaded...

If the spectrogram looks any different between the int16 and the float32 versions it sounds like the spectrograms are computed differently. There are a lot of parameters to play around...

I haven't tried installing the pre-release of tensorflow that you are using, but everything works fine in the current version. If this is an unstable pre-release they might fix things...

Hey Sam! Yes I'm back doing ephys again after working in just behavior for a while. Here is how I computte recording _cmr ``` recording = se.read_openephys(folder_path=sort_path, block_index=0) recording =...