MedSegDiff
MedSegDiff copied to clipboard
KidsWithTokens
assert x_t.shape == eps.shape
你好，我在对于DRIVE数据集上进行采样时，出现了这样问题，请问我该如何解决呢
Traceback (most recent call last):
File "E:\deep_learning\Segmentation\MedSegDiff-master\scripts\segmentation_sample.py", line 214, in
你好，我在对于DRIVE数据集上进行采样时，出现了这样问题，请问我该如何解决呢 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
same question
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，所以我将eps就只取了第一通道，就跑通了
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
I try to print their shapes, which are x_t: torch.Size([1, 1, 64, 64]), eps: torch.Size([1, 2, 64, 64]), and then I print out the Data, I found that the data of his two channels are the same, so I only took the first channel of eps, and it ran through.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
But I still have my doubts about the cause of the problem.
但是我对于问题出现的原因，还是存有我的疑问
How is your segmentation effect? After running this experiment, I feel that the segmentation results are not as good as UNet
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，所以我将eps就只取了第一通道，就跑通了
My solution is the same as yours
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
But the effect I ran out was a bit poor.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
What is the effect on the data set you ran?
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
Brother, how many steps have you trained to achieve this effect?
But the effect I ran was a bit bad
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
Brother, how many steps have you trained to achieve this effect?
But the effect I ran was a bit bad
应该是10000左右