GuillaumeErhard / Supervised_contrastive_loss_pytorch

Independent implementation of Supervised Contrastive Loss. Straight to the point and beyond
MIT License
75 stars 11 forks source link

Low Val Accuracy on CIFAR 100 #2

Open chaitanyaanimesh opened 2 years ago

chaitanyaanimesh commented 2 years ago

Do you mind sharing the parameters you used for training CIFAR 100? For me validation accuracy seems to be saturating at 40% (using resnet-20 though) even with Auto Augment=True. I am interested in knowing the learning rate, batch size, resnet model and temperature you used for CIFAR-100.

Angelina1996 commented 1 year ago

Could you please guide how to run this code for ImageNet dataset