Daniel Geiger
Daniel Geiger
I was not saying the paper claimed to have checkpointing based on validation loss, while the code doesnt. I was just expecting it to have this feature, as it is...
Btw Mediar did the same. So either they just blindly copied their semantic or I am missing something.
> [@le1nax](https://github.com/le1nax) I'm not sure where the paper says that the mse is scaled, but the relevant equation from the cellpose 1 paper is > > > which is what...