Nanne

Oops, it seems `extract_features()` is also used in net_vlad_img.py and netvlad_img_sfrs.py, and I think my changes will break the code there. It looks like the training code can be fairly...

Haven't done any extensive testing on it, other than like a first couple of iterations just to see it trains. How much worse is the performance?

that's very surprising, but a clear indication something is definitely going wrong. I won't have much time to work on this, but I'll try to see if I can figure...

Thanks for doing these comparisons, seems like it indeed doesn't generalise too well to the Tokyo 24/7 dataset. Previously I noticed that if I start training from the matconvnet vgg16...

Debugging why something doesn't generalise to another dataset is quite tricky, but perhaps you can try some checkpoints from earlier in the training process, and see if it overfits to...

I saw similar performance differences between val and test, so seems to be normal yes. Performance after 1 epoch seems similar to what is reported in the netvlad paper for...

The Tensorflow repo you linked appears to re-use the original MATLAB models, so I think the problem is essentially the same one; following the same training procedure doesn't give the...