search

vbalnt / tfeat

TFeat descriptor models for BMVC 2016 paper "Learning local feature descriptors with triplets and shallow convolutional neural networks"
MIT License
148 stars 45 forks source link

how to evaluate the Liberty using Notredame #12

Closed hurricane2018 closed 6 years ago

hurricane2018 commented 6 years ago

image

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 ?

hurricane2018 commented 6 years ago

how many epoches did you use to evaluate a dataset ?

hurricane2018 commented 6 years ago

In your code, you only train 10 epoches. But if we do several experiments, each time we can get a test result. So did you try several times, and then average them ?

vbalnt commented 6 years ago

Training code with the evaluation part is now available as an ipython notebook.