Closed Rokinluohhh closed 6 months ago
We provided the version of pytorch-lightning related packages (timm==0.6.12), and the rest does not matter. If you encounter any problems, please let me know.
Thanks for your reply!Have you stained and normalised the patches?
No.
Hi,can you provide your code for creating patches?
The patches come from a previous project from our co-authors around two years ago. I will contact them to see if they still have that code.
ok,thans very much.And may I ask if you used cross validation?
No, we use fold=0 as the validation set and repeat the experiment 3 times.
ok Thanks for your patient reply!
Hi,why you reshape there?
Because we use merged images. For 200 merged images of 224x 224, it shape is h=224*200, w=224, c=3. This reshaping operation convert it back to (200, 224, 224, 3).
So,I should change this code if i use images that havent merged?
No, you do not need to. This code is capable with images not being merged. The reshaping operation will result in (1, 224, 224, 3).
Thanks a lot!
Can you provide the version of the packages(such as timm)? Looking forward to your reply!