FengheTan9 / Multi-Level-Global-Context-Cross-Consistency

Official Pytorch Code base for "Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Model"
MIT License
33 stars 1 forks source link

dataset split #13

Open feililucky opened 6 months ago

feililucky commented 6 months ago

Hello, I saw in your paper that we utilize all cases and randomly split the BUSI dataset into 70-30 ratios three times (i.e., 526 samples for training and 254 samples for validating) to ensure fair comparison., but I based on In your split.py code, I found that the final training set is 546 and the test set is 234. Which one should I use as the standard? Thank you