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

hardnet training files #28

Closed aIR1000 closed 6 years ago

aIR1000 commented 6 years ago

Hello,

Can you please elaborate the differences in hardnet.py , hardnetclassicalhardnegmining.py and hardnetclassicalhardnegminingsiftinit.py?

Also, when I run run_me.sh, the default experiment is train on liberty and test on yosemite and notredame?

DagnyT commented 6 years ago

HardNet.py - main file for training/evaluating HardNet hardnetclassicalhardnegmining.py and hardnetclassicalhardnegminingsiftinit.py - classes that were made for evaluation of hard negative mining in classical way (when you pre-select hard negatives from the whole dataset) and the same but mining is done via sift descriptor.

Yes, training with liberty split, test on notredame and yosemite.

aIR1000 commented 6 years ago

Thanks a lot!