search

zhmiao / OpenLongTailRecognition-OLTR

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)
BSD 3-Clause "New" or "Revised" License
839 stars 128 forks source link

hyper-parameters #45

Closed JasAva closed 4 years ago

JasAva commented 4 years ago

Hi, I'm curious if you could give some insights on how to decide the value of hyper-parameter scale (currently is set to 16) in the CosNormClassifier, is it set empirically or is there a theoretical way to set it? Also the parameter scale (currently is set to 10) in meta-embedding for reach-ability.

zhmiao commented 4 years ago

Hello @JasAva , these hyperparameters were tuned based on original implementations or other people's experiences. We would use their numbers first and then gradually tune these parameters to get better performance. Does that make sense?