Getting Epoch-600 0.7719 0.8504 0.9052 0.9451 0.9701 0.9847 with Binomial on Cars196

bnu-wangxun / Deep_Metric

Deep Metric Learning

Apache License 2.0

778 stars 148 forks source link

Getting Epoch-600 0.7719 0.8504 0.9052 0.9451 0.9701 0.9847 with Binomial on Cars196 #49

Open LinkToPast1990 opened 4 years ago

LinkToPast1990 commented 4 years ago

Hi, @bnu-wangxun I want to reproduce the result of Binomial Loss, so I modified the run_train_00.sh slightly:

DATA=car
...
LOSS=Binomial
...
DIM=64

And I downloaded the bninception from here.

But I get a performance Epoch-600 0.7719 0.8504 0.9052 0.9451 0.9701 0.9847, which is similar to MS Loss. Any idea about this? Thanks!

bnu-wangxun commented 4 years ago

Good result. When I write the paper, the code is not with all tricks and the optimal optimizer. So the result is a bit worse than the code. If you use MS loss with this code, you will reach the result about recall@1 > 80%. The results will be better consistently.