tara0907

Firstly, I would like to express my sincere gratitude to the author for being able to open source this work. I am very interested in your work, but I encountered...

Hello, the only result I reproduced on the CIFAR100 dataset using WRN_40_2 (teacher) and WRN_40_1 (student) is a classification accuracy of 72.79%, which is significantly different from the result of...

Base result reproduction problem

1

Hello, I'm very interested in your work. I'm currently trying to run a baseline using a single-branch CNN student network (resnet50 and resnet34). After disabling ptc_loss and sim_loss, I've tried...