Hey @tomwhite, I just got around to run predict from your work in f1812ffdd659eab09fcf18ecfab626f10dd8334d to get it deployed on AWS. One thing I noticed is that the Zarr file that you use in the predict_test produces a bunch of NaN values in the resulting GeoJSON.
It's no biggie - apparently NaN is fine in JS, just not valid JSON - but I'd like to understand where they come from and if we can get rid of them. I did check whether the system_id doesn't exist in the model, but it does.
Hey @tomwhite, I just got around to run
predict
from your work in f1812ffdd659eab09fcf18ecfab626f10dd8334d to get it deployed on AWS. One thing I noticed is that the Zarr file that you use in thepredict_test
produces a bunch ofNaN
values in the resulting GeoJSON.e.g.
It's no biggie - apparently
NaN
is fine in JS, just not valid JSON - but I'd like to understand where they come from and if we can get rid of them. I did check whether thesystem_id
doesn't exist in the model, but it does.Do you have any ideas?