Hello!

I am currently researching the use of HIPT (Hierarchical Image Pyramid Transformer) for feature extraction from whole slide images (WSI). I have thoroughly read your paper and related documentation and successfully run some example codes. However, I am encountering difficulties when trying to extract features from lightweight slices.

Specifically, I would like to know:

How can I use HIPT to extract features from lightweight slices (for example, using ResNet-50 or ViT models at different resolutions)?
Are there any specific scripts or files that need to be run to generate these features? If so, could you please let me know the names of the relevant files and how to run them?
I am currently working with standard WSI datasets (such as TCGA) and have completed the data preparation according to the steps provided in the documentation. I would greatly appreciate any guidance or reference materials you could provide.

Thank you very much for taking the time to read this email. I look forward to your response!

Best regards