search

DagnyT / hardnet

Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
MIT License
514 stars 100 forks source link

HPatches result with matlab and python #36

Open aIR1000 opened 5 years ago

aIR1000 commented 5 years ago

Hello,

I have tested your pretrained model of liberty with augmentation with python implementation of HPatches. I was able to reproduce results but when I tested with matlab implementation of HPatches to generate graphs I wasn't able to reproduce retrieval results (patch verification and matching results were correct.) can you please guide what I possibly be doing incorrect. Split is "full", I have checked. Does it has something to do with distractors?

Hardnetlibertywithaug (mAP with python implementation) = 69.66 Hardnetlibertywithaug (mAP with matlab implementation) = 60.64

Thanks in advance

appleleaves commented 4 years ago

I believe the split is not correct. I checked it a year ago. Hope it could help you.

clelouch commented 4 years ago

I've also found the problem, you can use another branch. https://github.com/hpatches/hpatches-benchmark/tree/ench/matplotlib-fig