Need to Modify Config Files to Reproduce Results from the Paper?

[MyFirstKindom]

Hello,

I am attempting to reproduce the results presented in the paper [Title of the Paper]. Could you please clarify whether it is necessary to modify the config files provided in the repository? If so, could you provide guidance on which specific parameters or sections need to be adjusted to achieve the same experimental setup as described in the paper?

Thank you for your assistance.

[MyFirstKindom]

This is the result of my run, and it seems to be slightly different from the one in the paper.

[MyFirstKindom]

This is the instruction I use for evaluation：
python evaluation.py --lr_dir=../logged_files/CIFAR10/10/ConvNet/my_run_name/Normal/lr_best.pt --data_dir=../logged_files/CIFAR10/10/ConvNet/my_run_name/Normal/images_best.pt --label_dir=../logged_files/CIFAR10/10/ConvNet/my_run_name/Normal/labels_best.pt --zca

[GzyAftermath]

Sorry for the late response.
Maybe it's because you didn't change the parameters used in training the expert models. (As we reported in the paper, we generate expert trajectories in the same way as FTD without modifying the involved hyperparameters.)
So please refer to the FTD paper to get the hyper-parameters used in buffer.py