search

hitachinsk / SAMed

The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"
MIT License
468 stars 43 forks source link

No much performance difference between SAMed and SAMed_h on my own dataset #48

Open maosuli opened 4 months ago

maosuli commented 4 months ago

Thanks for your code. However, I found that there existed less performance difference between SAMed and SAMed_h for my own dataset.

May I know how to fine-tune the parameters to improve the performance of SAMed_h? Shall I change the rank of LoRA adaptation?

Best,

Eric

luobendewugong commented 4 months ago

Thanks for your code. However, I found that there existed less performance difference between SAMed and SAMed_h for my own dataset.

May I know how to fine-tune the parameters to improve the performance of SAMed_h? Shall I change the rank of LoRA adaptation?

Best,

Eric

Hello, I noticed that you have trained using your own dataset. Could you please advise me on how to convert my own dataset into training and testing datasets usable for Samed? Thank you very much!