search

facebookresearch / dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Apache License 2.0
6.06k stars 885 forks source link

Linear Evaluation LR Sweep Values #249

Open ferreirafabio opened 11 months ago

ferreirafabio commented 11 months ago

Hi, in the paper, you write "For each model, we sweep the learning rate value.". What are the swept learning rate values?

Thank you.

ferreirafabio commented 11 months ago

@mathildecaron31 would be highly appreciated :)