search

titu1994 / keras-one-cycle

Implementation of One-Cycle Learning rate policy (adapted from Fast.ai lib)
MIT License
285 stars 78 forks source link

self.scale in compute_lr #3

Open yaroslavb1 opened 6 years ago

yaroslavb1 commented 6 years ago

In lines 103 and 107, the formula should be 1 / self.scale instead of self.scale * 100.