M-Nauta/PIPNet

Resnet50 Model

ThomasNorr opened this issue · 3 comments

ThomasNorr commented

Hello and thanks for your fascinating work,

Would you mind uploading a resnet50 model (or even better one for Cars and one for CUB) or/and providing the arguments needed to reproduce the results on that architecture? Or are resnet50 parameters equal, except for the mentioned differences in the paper?

Greetings

wudemoai commented

Hello, did you repeat this article? I set the training hyperparameters on the CUB200 data set according to the author's document, but I encountered some problems and did not get the corresponding weights.

ThomasNorr commented

ya, I got roughly the same.

M-Nauta commented

Hi all, thanks for your interest in PIP-Net! Sorry that it took so long but the trained checkpoints are now uploaded and added to the README, allowing to reproduce results of the paper.