[minor] Properly label losses when training neural networks

ECMWFCode4Earth / ml_drought

Machine learning to better predict and understand drought. Moving github.com/ml-clim

https://ml-clim.github.io/drought-prediction/

90 stars 18 forks source link

[minor] Properly label losses when training neural networks #68

Closed gabrieltseng closed 5 years ago

gabrieltseng commented 5 years ago

Currently, the model is trained using smooth l1 loss, and the evaluated using RMSE; this makes it hard to gauge the performance of the model on the test set vs training set.

This PR ensures the training RMSE is also calculated and printed.