Closed StephenHausler closed 2 years ago
Instead of hardcoding, can't we use eval_set.qIdx
and eval_set.pidx
?
Also, what are the recalls for Patch-NetVLAD (compared to vanilla NetVLAD)?
Instead of hardcoding, can't we use
eval_set.qIdx
andeval_set.pidx
?
I don't think so, since msls concatenates the two datasets together. So eval_set.qIdx contains a list of query indices that are from both datasets.
I've made changes that now means that val.py should work in the general case, with any combination of mapillary cities. Please re-review and let me know your feedback.
Thanks, lgtm! What do you think @oravus?
Yep, this should do (ignore my earlier comment). EDIT: Re-opened
Agreed that it's not very nice atm. I've got a plan, let me fix tomorrow
Fix #43
Hey @StephenHausler @oravus - I think https://github.com/QVPR/Patch-NetVLAD/pull/44/commits/f06d664be907d1926d0aa0de1e2cb6305a2ba007 makes it a bit cleaner. I did "open loop" coding though and haven't tested if it still works properly - could you please check @StephenHausler?
I've just tested the code, it works perfectly. Thanks Tobi for your refactor, looks great
Made changes to val.py that should fix the indices issue that was causing low reported recalls for mapillary validation on the cph and sf datasets. Without PCA, the recalls with NetVLAD (with the mapillary trained model) are now: 0.495, 0.65, 0.718, 0.77, 0.83, 0.868.