Open TBdt38 opened 4 years ago
Hmm interesting idea. Some things that are particularly influential are the anchor box scales and aspect ratios. Maybe also the number of anchor boxes. Apart from that, there's not much that you can really do a sweep over.
ok nice, i keep that in mind, thanks!
do you have the exact parameter names you mentionned? there are plenty of parameters available in config.py file :) thanks
They are pred_aspect_ratios
and pred_scales
. Check yolact_base_config
for details.
@TBondat "run like bayesian optimization to tune some hyperparameters of yolact" can you please elaborate on this is there any different way to tune the hyperparams
yes, you can also do basic grid search or random search for instance. https://nanonets.com/blog/hyperparameter-optimization/
Hi, as i'm running smaller dataset than the full coco + doing fine-tuning, it doesn't take so much time to get reasonable results. So i was thinking to maybe try to run like bayesian optimization to tune some hyperparameters of yolact.
Which hyperparameters do you advise me to release, to run the optimization? which ones are the most influent / interesting? thanks