search

OSUPCVLab / MobileUNETR

Official Implementation of MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer For Efficient Medical Image Segmentation (ECCV2024) (Oral)
39 stars 4 forks source link

How should I process the data #6

Open tpwxtd opened 3 weeks ago

tpwxtd commented 3 weeks ago

2222 11111

tpwxtd commented 3 weeks ago

The file path's encoding is windows-1254, but when I switch from UTF-8 to windows-1254, I still get the same error.

srperera commented 1 week ago

Im not sure why this is happening. All of our experiments were on linux and in out csv file we just had 2 columns one for image path and the other for the mask. and it worked out perfectly. Because if you look at the data loader we are doing a simple image loading process. Please let me know if you are running into additional issues. If the current dataloader does not work on windows, you can make a slight modification and as long as the getitem method is returning something similar the rest of the pipeline should work.

tpwxtd commented 1 week ago

111 Thank you for your reply. I have processed the data, but I encountered the error shown in the above image when running the code. I have searched online for related information, but was unable to resolve it. If you could help me fix this issue, I would be very grateful.

Im not sure why this is happening. All of our experiments were on linux and in out csv file we just had 2 columns one for image path and the other for the mask. and it worked out perfectly. Because if you look at the data loader we are doing a simple image loading process. Please let me know if you are running into additional issues. If the current dataloader does not work on windows, you can make a slight modification and as long as the getitem method is returning something similar the rest of the pipeline should work.