how many epoches did you use to evaluate a dataset ?

ColumbiaDVMM / Spread-out_Local_Feature_Descriptor

Code for Learning Spread-out Local Feature Descriptors

39 stars 14 forks source link

how many epoches did you use to evaluate a dataset ? #4

Closed hurricane2018 closed 6 years ago

hurricane2018 commented 6 years ago

The test accuracy is always change. Did you get the average precision of the test data ?

I mean, If we train 10 epoch, we can get a precision. If we train 20 epoches, we can get another result. How did you solve this problem ?

spongezhang commented 6 years ago

Hi Hurricane,

Due to randomness of the network training, the performance will change. It's true for all the DL based methods. We generally learn 10 epochs and take the average of 3 different trials.

Best, Xu

hurricane2018 commented 6 years ago

Ok, got it. Thanks!