YuLong Shi

Results 3 issues of YuLong Shi

作者你好,在复现实验时出现如下问题,烦请解答。 按照readme文档配置后,使用mms数据集测试时发现dice和assd极低,使用wandb在test_run.py跟踪后结果如图 ![image](https://github.com/HiLab-git/UPL-SFDA/assets/102472253/847aa753-6d57-498e-beba-94a0f6888a0c) 结果并不收敛且跳动较大。该结果是原始数据集裁剪时间轴后训练的,使用的原模型是MMS_model-source.pth。部分域适应结果如图: ![结果拼图1](https://github.com/HiLab-git/UPL-SFDA/assets/102472253/f0d1a157-1706-43ab-acea-019ec960e584) 想请教下您对于这个结果有什么建议,可以提升最终结果。 此外,还有一个疑问: MMS数据集裁剪时间轴后为3D图像,为何在示例源码中train2d_source.cfg则是使用该数据集? 感激不尽!! 祝科研顺利

Thanks for your great work, but i find a problem during the inferece stage. When i used the pretrained model to predict cine MRI, I find the prediction is update...

The work of the paper is very impressive I would like to ask about the preprocessing of your dataset. I have seen that your dataset is not the original BTCV...