Fixing val.py incorrect recalls issue #43

[StephenHausler]

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.

[Tobias-Fischer]

Instead of hardcoding, can't we use eval_set.qIdx and eval_set.pidx?

[Tobias-Fischer]

Also, what are the recalls for Patch-NetVLAD (compared to vanilla NetVLAD)?

[StephenHausler]

Instead of hardcoding, can't we use eval_set.qIdx and eval_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.

[StephenHausler]

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.

[Tobias-Fischer]

Thanks, lgtm! What do you think @oravus?

[oravus]

Yep, this should do (ignore my earlier comment).
EDIT: Re-opened

[Tobias-Fischer]

Agreed that it's not very nice atm. I've got a plan, let me fix tomorrow

[Tobias-Fischer]

Fix #43

[Tobias-Fischer]

Hey @StephenHausler @oravus - I think f06d664 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?

[StephenHausler]

I've just tested the code, it works perfectly. Thanks Tobi for your refactor, looks great