Diffusion-based-Segmentation

Diffusion-based-Segmentation copied to clipboard

NaN values

4

@JuliaWolleb 1) Getting nan values in very early stages of training why is that? what might be going wrong? Kindly let me know how to solve the nan issue. -------------------------...

saisusmitha

fully expect!Next few days?

YonghanLU

Input of size

4

Hi JuliaWolleb: I encountered the following error while running, RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [1, 5, 240, 224, 139] how...

Lateryears

Hi there, nice work. Can you please provide the training testing split you used for the brats dataset?

rtx98

Hi, Can you please tell me the steps to update the script to perform a multi-class segmentation on the inputs? Best, Chinmay

chinmay5

testing error

2

Hello, I encountered an error during prediction. Can you tell me why this happened? Traceback (most recent call last): File "/root/autodl-tmp/scripts/segmentation_sample.py", line 130, in main() File "/root/autodl-tmp/scripts/segmentation_sample.py", line 97, in...

lanlinxxs

Hi, thank you for providing the code. I have a question about the `ddim_sample_loop_known` function. Why do we set the timesteps in this line (https://github.com/JuliaWolleb/Diffusion-based-Segmentation/blob/676f214035e90edd0357f51feab45841e4aefcfb/guided_diffusion/gaussian_diffusion.py#L792) to be 499? Shouldn't the...

bennymi

Sample during training problem 2

2

I saw that there was a discussion about this issue before, but it was closed. However, I still have a question to ask. could you tell me how to go...

RainJayAn

hello, do you mind sharing brats pretrain model ? i want use it for infer.

wangnanv5

 i add kvasir-seg dataset(1000 samples) to source code and modify some below:   kvasir-seg consists of img and mask with 3 channels and 1 channel respectively. and in...

ssxfc