You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is a feature request. Since there is already a save_model function, a load_model is needed. Also I think save_model should be called in the train loop as well, to be able to resume training from some epoch.
Btw thanks for providing the code, it's very surprising that such a simple model can perform that well.
The text was updated successfully, but these errors were encountered:
I will add a testing case on the test2015 soon. It would load the trained model then evaluate it on the test2015 data and create the csv which could be submitted to the evaluation server.
This is a feature request. Since there is already a
save_model
function, aload_model
is needed. Also I thinksave_model
should be called in the train loop as well, to be able to resume training from some epoch.Btw thanks for providing the code, it's very surprising that such a simple model can perform that well.
The text was updated successfully, but these errors were encountered: