MedSegDiff icon indicating copy to clipboard operation
MedSegDiff copied to clipboard

Medical Image Segmentation with Diffusion Model

Results 77 MedSegDiff issues
Sort by recently updated
recently updated
newest added

Could you please upload the DDIT dataloader and its config settings? I am trying to reproduce your results in the paper but am unable to acheive them. Thank you.

After trainning for 17W steps, I can get good results without using dpm-solver in 1000 steps, as shown below: ![image](https://github.com/WuJunde/MedSegDiff/assets/61099841/19a66838-54c2-4714-98e7-2871d75741ef) However, when using dpm-solver in 20, 50, or 1000 steps,...

run_loop函数里,哪个参数代表运行次数

Hi I have trained the segmentation code on dataset ISIC. But when I am running sample I am getting the following error. I have used all the default parameters suggested...

Thank you for your outstanding work, can you share the pretrained model

Thanks for your great work. I follow the README defualt setting, just change the `dpm_solver = True`. The result show as followed. ![image](https://github.com/KidsWithTokens/MedSegDiff/assets/76839625/ef78dd73-d905-4f85-b8d8-316b9cb34da3)

生成了三个 emasavedmodel,optsavedmodel,savedmodel 我不知道这三个分别是什么意思 有人给我解释一下吗 plz

我根据您提供的代码已经成功运行了自己的数据集,但是在测试阶段每个样本需要消耗大量的时间进行输出预测。请问您是如何解决这个问题的呢?在测试过程中,我看您并没有调整diffusion_steps,也没有用到DDIM或者DPM_solver