General Questions

[AmeenAli]

Hello I have a few questions regarding the code,

1. In a previous issue I asked about a checkpoint file and you asked me to use the one from https://github.com/yukimasano/self-label/ for example, my question is what is the training being done in the eval_linear_probes.py? if I train using this script and evaluate later will I get the same numbers as in your paper? if not how can I re-produce thanks best

[yukimasano]

Hi there, For reproducing the numbers in the self-label paper, yes just use the checkpoint that is available from that repo. For reproducing the "single-image" numbers, just use the original repos RotNet or DeepCluster repos, both PyTorch. Cheers, Yuki

[AmeenAli]

@yukimasano Hi , thanks for your response however I'm still unable to get the model for a single imge expermint, any chances you can upload it (for images A,B) or otherwise , tell me how to train it from scratch? thanks!