appleleaves
appleleaves
is the training model available yet? Thanks
I believe the split is not correct. I checked it a year ago. Hope it could help you.
I use the python to calculate the mAP which is not equal to the answers on the paper, but equal to the auc result of the matlab code. I think...
OK, thanks for replying in short notice. That make me confuse for so long a time. And I am now more sure about my judgement.
Here is the bug I think appear, and I am not familiar with the AUC calculation, so it would be nice if you check it yourself. ## matlab code eval.m...
@lenck
what I mean is that, when you work with the retrieval task, and set all the descriptors to ones. Therefore, **the descriptors are useless, because all the descriptors are all...
I think the patches are already extracted! You should read the paper or the matlab code "sift.m". You should describe the patch only. This dataset extracts the patches in its...
In the file main_binary.py line 252, there is the loss.backward(). I think the backward pass has already done! Also, are you really sure that the weights are not changing? Maybe...
Did you solve the problem? I think it was because all the output get close 0, so the loss2=0 and loss1=0.125