MedicineToken / MedSegDiff

Medical Image Segmentation with Diffusion Model
MIT License
1.06k stars 166 forks source link

一些问题的解答/Answers to some questions for training and sampling #195

Open MilkTeaAddicted opened 2 weeks ago

MilkTeaAddicted commented 2 weeks ago

看到这里很多issue没有人回答,作者也没怎么维护,我结合我自己实验的结果回答一下

  1. 为什么采样生成的图案是一片漆黑? 训练出了问题,大概率training过程的步数不够,多训练一会

  2. training的epoch在多少比较合适 我个人实验的结果显示epoch大概在60000次左右效果开始变好

  3. 代码没有设置收敛标准,怎么让training停下来 需要手动停止,停止的标准可以参考上一步我实验得出的结果

  4. 代码生成了三个模型,用哪一个采用会比较好 emasavemodel.pt做采用的效果会比较好

Issues-translate-bot commented 2 weeks ago

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿


I see that many issues here have not been answered, and the author does not do much to maintain them. If you have obsessive-compulsive disorder, I will answer them by myself based on experiments.

  1. Why is the pattern generated by sampling completely black? There is a problem with the training. There is a high probability that the number of steps in the training process is not enough. Please train for a while.
  1. What is the appropriate epoch for training? The results of my personal experiments show that the effect starts to get better around 60,000 epochs.

  2. The code does not set a convergence standard. How to stop training? It needs to be stopped manually. The standard for stopping can refer to the results of my experiment in the previous step.

  3. The code generates three models, which one is better to use? The effect of using emasavemodel.pt will be better

WuJunde commented 2 weeks ago

Greatly appreciate your contribution.