Giters

Harvard-Ophthalmology-AI-Lab / FairSeg

[ICLR 2024] FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling

Home Page:https://ophai.hms.harvard.edu/datasets/harvard-fairseg10k/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

problem of FairDiceLoss

1819707238 opened this issue · comments

commented

你们所提出的这个FairDiceLoss似乎忘记了在文中使用？ 仅在train_novel.py文件中引入并进行了定义，但似乎并未参与计算？

commented

你们所提出的这个FairDiceLoss似乎忘记了在文中使用？ 仅在train_novel.py文件中引入并进行了定义，但似乎并未参与计算？

Please run train_finetune.sh and it will call trainer_novel function and inside the function there is one line to define the FairDiceLoss here: dice_loss = FairDiceLoss(num_classes + 1, n_attr=sens_classes, gamma=args.gamma)