Open Crista23 opened 6 years ago
use tensorboard to monitor model accuracy and loss.use ctrl+c to stop the model --you can fire back train.py to resume training.run eval.py to see how you model has performed. this file is usually linked to validation sets which you can update as you wish.
I can see the model is training for a fixed number of epochs and there is no validation set. How do you know when to stop model training, and also how to add one? Thank you!