Closed arpit601 closed 7 years ago
Training goes on until you abort. It outputs whenever it saved Model saved.
.
You can specify how often it shall save with --steps-per-checkpoint
Lets say I put 1000 files for training and give batch size as 10 , then after running it for 1000 global steps what should be the number of epochs ?
well epochs = number of iterations through dataset therefore
examples_seen = batch_size * steps
epochs = examples_seen / training_set_size
10 * 1000 / 1000 = 10 epochs
How do you set the number of epochs for training ?
epoch-count flag comes in evaluation file,..