You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Added mutli-scale performance on roxford5k and rparis6k for new pre-trained networks with end-to-end whitening, trained on both retrieval-SfM-120 and google-landmarks-2018 train datasets
Added a new example test script without post-processing, for networks that are trained in a fully end-to-end manner, with whitening as FC layer learned during training
Added few things in train example: GeMmp pooling, triplet loss, small trick to handle really large batches
Added more pre-computed whitening options in imageretrievalnet
Added triplet loss
Added GeM pooling with multiple parameters (one p per channel/dimensionality)
Added script to enable download on Windows 10 as explained in Issue #39, courtesy of SongZRui