Closed carlcorder closed 6 years ago
Both! You can follow the original repo recommendations for this here:
Tuning your models is kind of a "dark art" at this point. In general:
Thank you for your very thoughtful and organized answer! I'll keep this comment as reference while training models in the future.
The suggested hyperparameters have a dropout of 0.25. However, it's unclear which option to use with
train.py
in order to achieve this?My guess would be either
output_keep_prob
orinput_keep_prob
but I'm not sure.Thanks!