William Smith

Results 3 issues of William Smith

Hi, firstly thank you for making this code public! I am currently looking to reproduce some of the experiments done in the NetVLAD paper. To do this I'd like to...

The initial Nordland set uses images that have been downsampled at intervals of 10. The filename numbering specifically reflects this and the program can only take new images if they're...

Changing the subsample factor in the GUI results in a fatal error in the results calculation. For example, changing the factor from 10 to 5 and removing the ground truth...