search

bertinetto / cfnet

[CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..
MIT License
523 stars 156 forks source link

hyperparameter optimization #16

Open zhanglichao opened 6 years ago

zhanglichao commented 6 years ago

hi Luca,

So how to set random vectors of hyperparameters?

thanks

bertinetto commented 6 years ago

Just define arrays of suitable values and take one random index per array per iteration.