Where is the code for choosing hard class-m ?

[gerber]

Hi, I have read your paper.
In section 4.3 Hard task (HT) meta-batch, it says that "We choose the failure class-m
from each task by ranking the class-level accuracies ..."
May I ask where is the code for choosing hard class-m ?
Thanks

[Yaoyao Liu]

Thanks for your interest in our work.
The code for HT meta-batch has not been merged to the current project.
I'll let you know when it is updated.

[gerber]

Will it be merged soon?

[Yaoyao Liu]

I am not pretty sure. If I have time after the NeurIPS deadline, I will update the entire PyTorch project.

[gerber]

OK, thanks

[Daniel123jia]

I am not pretty sure. If I have time after the NeurIPS deadline, I will update the entire PyTorch project.

Excuse me, two years have passed. Has it been updated yet?

[Yaoyao Liu]

Hi @Daniel123jia,

Thanks for your interest in our work. I am sorry that I didn't update this GitHub repository on time. I have to say, currently, I cannot guarantee a deadline to update this repository.

If you have any difficulties using my project, please contact me via email: [e-mail]
I can share our original code with you. I hope this can help you apply our method to your work. If you have any further questions, I am also very happy to discuss them.

Best regards,

Yaoyao

[Clara2333333]

Excuse me，I am also interested in the code for Hard task (HT) meta-batch. I have sent email to [e-mail]. Looking forward to your reply,thank you very much!!!

[Yaoyao Liu]

Excuse me，I am also interested in the code for Hard task (HT) meta-batch. I have sent email to [e-mail]. Looking forward to your reply,thank you very much!!!

Thanks for your interest in our work. I think I've replied to your email. If not, please feel free to contact me again.

[Clara2333333]

Excuse me，I'm so sorry to interrupt you again. I sent another email and I am not sure whether I miss your reply.

[Clara2333333]

Excuse me，I am also interested in the code for Hard task (HT) meta-batch. I have sent email to [e-mail]. Looking forward to your reply,thank you very much!!!

Thanks for your interest in our work. I think I've replied to your email. If not, please feel free to contact me again.
Excuse me，I'm so sorry to interrupt you again. I sent another email and I am not sure whether I miss your reply.

[Clara2333333]

I am not pretty sure. If I have time after the NeurIPS deadline, I will update the entire PyTorch project.

Excuse me, two years have passed. Has it been updated yet?

Excuse me，may I ask have you got the code?