SueeH

> You were using initial learning rate lr=0.1 with arcface loss, it almost like re-train from scratch. Can you try to set lr = 0.005, and also try triplet loss...

> After some toying with glint/glint-asia fine tuning, I realized you wouldn't necessarily get better accuracy on validation sets (lfw, cfp_fp, agedb_30) after the fine tune. It should be close...

> I've got a better performance on my own dataset,whats U should do is being patient and down your lr to 0.01,0.005 and 0.001 better performance on your own dataset?...

I use Euclidean distance，for two normalized vector v1 v2，||v1-v2|| is calculated . Is any possible falconn v1.3.1 only find the local optimal value, rather than the global optimal value？

I used parameter as follows: params_hp.dimension = vec_len_; params_hp.lsh_family = LSHFamily::CrossPolytope; params_hp.distance_function = DistanceFunction::EuclideanSquared; params_hp.storage_hash_table = StorageHashTable::BitPackedFlatHashTable; params_hp.k =2; params_hp.l = 10; params_hp.feature_hashing_dimension = 8; params_hp.last_cp_dimension = 8; params_hp.num_rotations =...

> > Dear Contributors, > > I can't find valid EBB! dataset now. Could you provide a new Google Drive link to the dataset? Very appreciate about that! Any available...

I have find the problem, since Kintinuous use DLib, and I download the latest version DLib which depends on Opencv3,but Kintinuous can only depends on opencv2. To solve this problem,...