RepDistiller

RepDistiller copied to clipboard

Thanks for your sharing. Did all of experiments distillation work with the CE loss? I have a problem about this training strategy. First , well trained teacher model fixed parameters,...

XiXiRuPan

Hi, @HobbitLong @erjanmx , Thank you for the very interesting paper! Is it correct that the code can reproduce only the results for CIFAR? If so, is it possible that...

senya-ashukha

When i try to train a teacher model resnet50 on new dataset(cub200), the backbone is different with origin resnet50. one the one hand, it is too big to use big...

tiancity-NJU

when I try to train a teacher model on cub200(200 classes), I use resnet50 and batch size 64, It will out of memory, I use 16G GPU. I could run...

tiancity-NJU

hyperparameters for other methods

1

Hi, I want to know about the hyperparameters that used to train other methods. Are these methods well trained?

wukailu

the introduction of ContrastMemory

1

Thanks for your excellent work! I wonder how can I learn about the implementation of memory bank in the paper. Is it the same as the implementation of memory bank...

sanshanxiashi

questions about ContrastMemory

3

Hi, according to Eq.19 in the paper, linear transform gT and gS are conducted on the teacher and student, respectively, i.e., gT(t), gS(s). But as for your codes, the teacher...

jianxiangm

gjd2017

Hi, I am interesting of the visualization of correlation matrix in your paper, I would like to know about how to calculate the correlation matrix of logits across the full...

winycg

Add backward compat properties to CIFAR100 dataset classes

2

Hello, fan of your great work. In trying to reproduce your CIFAR100 results via README example commands, they would end up in an error, e.g., ```bash python train_student.py --path_t ./save/models/resnet32x4_vanilla/ckpt_epoch_240.pth...

ml-illustrated