yurun
yurun
@appleleaves for all the bn layers the affine parmameters are fixed at 1 and 0, but the mean and var are learned.
@appleleaves We are working on the journal paper, when it is done, new modes and training codes including a lot of modifications will be made avaliable.
Hi @guyrose3 , The evaluation protocol of the Brown dataset can be find in a lot of papers, the ROC curve is obtained by varying the distance threshold, you can...
Hi @guyrose3 Here is the early results on Hpatches http://www.iis.ee.ic.ac.uk/ComputerVision/DescrWorkshop/index.html
@httbupt http://matthewalunbrown.com/patchdata/patchdata.html
@valavanisleonidas Hi, 1) I used adam with no learning rate scheduler with lr=1e-2, momentum=0.9. 2)Training data is just the standard three splits of the UBC dataset, ie train on one...
@Ahandsomenaive Hi, I am planing to share my re-implemented codes of of sosnet together with a recent work in another repository (https://github.com/yuruntian/HyNet), since there was legal issues.
@valavanisleonidas Hi, I didn't sample triplets directly, instead, I sampled batches of matching pairs and form triplets inside the batch. Each epoch has N batches, and within a batch, B...