Confusion about the swin transformer code.

[guoyage]

Hello author, thank you for your wonderful research. I have a small problem. As can be seen from the research results of your paper, swin transformer module has a great impact on the performance of your model. When I try to adopt swin transformer module, I find that your code is missing the relevant codes of self.weights. I used a simple linear layer instead, but the results are not ideal. I hope you can clarify the source code of your self.weights, looking forward to your reply.

[FranklinNotOld]

Do you mean there's lack of a pre-trained weight in Informer part? If so, the Informer could be trained during the teacher training process. Or you could provide the complete error message of 'self.weights' so I can check whether I miss something.

[Petrichor625]

Hello,

Thank you for reaching out and for your interest in our work!

It appears that an earlier upload may have included files from a related project, which could have caused the missing components you encountered. We apologize for any confusion this may have caused. We have now uploaded the correct, complete version of the code, including all necessary modules and weights.

Please pull the latest version, and feel free to reach out if you have any further questions or encounter any other challenges—we’re here to support you.

Thank you again for your understanding and patience, and we’re excited to see your work with the updated code!