Unable to reproduce the results

[AlirezaSalehy]

Hi, first thanks for your decent job. I have an issue which is I cannot reproduce the results mentioned in the paper when training on MVTec and testing on ViSA, here are the training hyperparameters which were supposedly used for yielding the paper results.

Argument	Default Value
depth	9
n_ctx	12
t_n_ctx	4
feature_map_layer	[0, 1, 2, 3]
features_list	[6, 12, 18, 24]
epoch	15
learning_rate	0.001
batch_size	8
image_size	518
seed	111

And in the table below there is a comparison of the two models' mean over class performance on ViSA (what i get and what is reported in the paper).

Object Name	Pixel AUROC (%) Me	Pixel AUROC (%) Paper	Pixel AUPRO (%) Me	Pixel AUPRO (%) Paper	Image AUROC (%) Me	Image AUROC (%) Paper	Image AP (%) Me	Image AP (%) Paper
Mean	95.4	95.5	85.8	87.0	81.2	82.1	84.6	85.4

Is there something that i am missing?
Thanks a lot in advance!

[zqhang]

Your hyperparameters are correct, and you maybe could slightly adjust the hyperparameters for better results.

[AlirezaSalehy]

I have tried in the past days, however i cannot reach the same performance as the checkpoints stored in the repository. Can you please explain in more detail which hyperparameters to adjust to reach the performance?
I appreciate your time.