attention-transfer icon indicating copy to clipboard operation
attention-transfer copied to clipboard

Strategy of α and β decay during training

Open d-li14 opened this issue 6 years ago • 0 comments

@szagoruyko @EderSantana Hi, your sharing code is appreciated, but would you please specify your strategy of decaying the two multipliers α and β during training process? Thanks in advance.

d-li14 avatar Aug 25 '18 09:08 d-li14