The checkpoint on iNat2018

dvlab-research / Parametric-Contrastive-Learning

Parametric Contrastive Learning (ICCV2021) & GPaCo (TPAMI 2023)

https://arxiv.org/abs/2107.12028

MIT License

241 stars 32 forks source link

The checkpoint on iNat2018 #15

Closed Duconnor closed 2 years ago

Duconnor commented 2 years ago

Thank you guys for your impressive work and releasing the code. I just wonder when will the checkpoint on iNat2018 be released? I'm looking forward to that. Thanks a lot!

jiequancui commented 2 years ago

Hi, thanks for your interest in our work.

We have already released the log file for checking. If you met problems with reproduction, welcome to discuss them with me.

We are being dedicated to an improved version of PaCo. It will take some time to re-train it and release the models.

Duconnor commented 2 years ago

Thanks for your quick reply, I've successfully reproduce the result. But I do think there is one tiny bug here https://github.com/dvlab-research/Parametric-Contrastive-Learning/blob/4609959c490a90698e379720e1a9d4a01edd94ac/LT/paco_lt.py#L530 which I think should be changed to total_logits = torch.empty((0, args.num_classes)).cuda()

jiequancui commented 2 years ago

Thanks for your suggestion.

I will fix the issue.