Bureaucrats, dave_user, Administrators
4,650
edits
Changes
→Train the model
==Building the application==
===Train Training the model===
The model is trained for a total number of 100 epochs, with early stopping to prevent model overfitting on train data and checkpointing the weights on best val_loss. After that, a new model is created disabling all the layers only useful during training such as dropouts and batchnorms (i.e. in this case the batchnorm layers are not used).