Question about pretrained teacher model

HobbitLong / RepDistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

BSD 2-Clause "Simplified" License

2.11k stars 389 forks source link

Question about pretrained teacher model #29

Closed MaorunZhang closed 3 years ago

MaorunZhang commented 3 years ago

Thanks for your work and code! I just fetched the pretrained teacher model(ResNet-110) from [http://shape2prog.csail.mit.edu/repo/resnet110_vanilla/ckpt_epoch_240.pth], and tested it with CIFAR-100. The accuracy is 70.27%, and in your paper the accuracy should be around 74%. Is there something wrong with this pretrained model?