Guilherme Castelão

My motivation was to have a more robust and well-defined NN. I'm afraid of the situation when I re-calibrate an NN with a slightly different normalization and forget to update...

@milancurcic , I have to check how you updated the library since the last time I worked on this and see if what I did is still consistent. If it...

@jvdp1 , thanks for your suggestions. I'll work on that. @milancurcic , yes, I have already rebased it with `main`. I'm interested in the loading from Keras output, but I...

Thank you very much @jdassink ! I believe I understand what's behind that bug. I'll check that tomorrow, as soon as I'm back to land (late in the day).

Hi @debboutr, Could you email that file to me so I can check what's the problem? My guess is that it was resolved with the new release 0.8.1. I'm not...

Hi @bucoyas , I need to double check, but I can't do that before tonight, maybe tomorrow. Sorry about that.

Thank you for the CNV sample file. Please check if you're using the latest version (0.11.4).

@bucoyas , thanks for reporting that. Sorry for the delay. The new release, 0.10.4, should resolve that. I'll keep this issue open until I have the chance to write a...

Thanks for reporting that. You'll need to update to seabird-0.12 or later. You can do that with PIP or wait a few minutes for conda-forge to update itself. Cheers, On...

Hi @guillotp , is this data (dCTD_2022_10_009.cnv) public? Where may I find it? Cheers,