Repository navigation
一些问题的解答/Answers to some questions for training and sampling #195
Description
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
-
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 -
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 -
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 -
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
Activity
Issues-translate-bot commentedon Oct 11, 2024
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.
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.
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.
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.
The code generates three models, which one is better to use?
The effect of using emasavemodel.pt will be better
WuJunde commentedon Oct 11, 2024
Greatly appreciate your contribution.
SkyLight99 commentedon Oct 30, 2024
@MilkTeaAddicted
Thank You for clarifying. can you mention what dataset you worked on? I trained BRATS2020 for 85K steps and still got black samples.
MilkTeaAddicted commentedon Nov 2, 2024
Hello, my dataset is ISIC2016, 60000 epoch, the integration effect of multiple pictures is as follows
The pictures generated each time are different. The one on the far right is the integrated picture.
2039551625 commentedon Nov 5, 2024
你好，请问可以帮我解决一下，我的这个问题吗？不胜感激
Traceback (most recent call last):
File "E:\deep_learning\Segmentation\MedSegDiff-master\scripts\segmentation_sample.py", line 214, in
main()
File "E:\deep_learning\Segmentation\MedSegDiff-master\scripts\segmentation_sample.py", line 123, in main
sample, x_noisy, org, cal, cal_out = sample_fn(
File "E:\deep_learning\Segmentation\MedSegDiff-master\guided_diffusion\gaussian_diffusion.py", line 565, in p_sample_loop_known
for sample in self.p_sample_loop_progressive(
File "E:\deep_learning\Segmentation\MedSegDiff-master\guided_diffusion\gaussian_diffusion.py", line 650, in p_sample_loop_progressive
out = self.p_sample(
File "E:\deep_learning\Segmentation\MedSegDiff-master\guided_diffusion\gaussian_diffusion.py", line 444, in p_sample
out = self.p_mean_variance(
File "E:\deep_learning\Segmentation\MedSegDiff-master\guided_diffusion\respace.py", line 90, in p_mean_variance
return super().p_mean_variance(self._wrap_model(model), *args, **kwargs)
File "E:\deep_learning\Segmentation\MedSegDiff-master\guided_diffusion\gaussian_diffusion.py", line 324, in p_mean_variance
self._predict_xstart_from_eps(x_t=x, t=t, eps=model_output)
File "E:\deep_learning\Segmentation\MedSegDiff-master\guided_diffusion\gaussian_diffusion.py", line 348, in _predict_xstart_from_eps
assert x_t.shape == eps.shape
AssertionError
MilkTeaAddicted commentedon Nov 5, 2024
不太懂你的报错，我在ISIC上没有出现过这种错误，而且check了一下你的调用栈，和我跑的代码一样
2039551625 commentedon Nov 5, 2024
我是在DRIVE数据集上跑的采样，然后我尝试打印他们的形状，分别为x_t: torch.Size([1, 1, 64, 64])
eps: torch.Size([1, 2, 64, 64])，然后我打印出eps中的数据，发现他的两个通道的数据是一样的，我很疑惑这一点
Issues-translate-bot commentedon Nov 5, 2024
I ran the sampling on the DRIVE data set, and then I tried to print their shapes, which are x_t: torch.Size([1, 1, 64, 64])
eps: torch.Size([1, 2, 64, 64]), then I printed out the data in eps and found that the data of his two channels were the same. I was very confused about this.
MilkTeaAddicted commentedon Nov 5, 2024
唔，没做过血管分割相关的工作，不过你的eps的shap是torch.Size([1, 2, 64, 64]) 要不试试沿着第二个维度拆分？调一下输入应该问题不大
Issues-translate-bot commentedon Nov 5, 2024
Well, I have never done any work related to blood vessel segmentation, but the shap of your eps is torch.Size([1, 2, 64, 64]). How about trying to split it along the second dimension? It shouldn't be a big problem if you adjust the input.
hourlass commentedon Feb 27, 2025
请问您实现在DRIVE上的分割了吗，是否可以交流一下
Issues-translate-bot commentedon Feb 27, 2025
Have you implemented the division on DRIVE? Can you communicate with me?
Luoqian524 commentedon Apr 27, 2025
hello,I would like to know how did you solve the problem that the sampled images are all black after you trained the model? The model you used is v1 or v2, thank you very much for answering my question, I've been troubled by this problem for a long time.
OnePlusRay commentedon Nov 23, 2025
您好，想问一下：
Issues-translate-bot commentedon Nov 23, 2025
Hello, I would like to ask: