Diffusion-based-Segmentation

Diffusion-based-Segmentation copied to clipboard

Can you tell me whether Nvidia 3090 with 24GB is able to train model?

4


Moriatyyuan

ABout Train result

2

Hi, I want to know if i successfully begain training. 

Ellenke

Can you tell me the code to convert the Brats2020 dataset into a dataset that can be directly trained as shown in this image? 

zhiwenliao

some checkpoints?

2

Would you please provide some checkpoints you trained?

xushilin1

multi-class segmentation discuss

6

Hi @JuliaWolleb , thank you for your great work. I want to solve the multi-class segmentation problem and I delete the "label = torch.where(label > 0, 1, 0).float()". Now, I...

smallboy-code

error when training on multiple gpus

1

I initialized the multiple training using torchrun, but it stuck here. Setting up a new session... Setting up a new session... Setting up a new session... Does anyone have an...

CNGaoWenbo

Image size

7

Why do you give the image_size flag value 256 when the slices are of size 240x240?

JesseWiers

Hi, thank you for sharing this code. I was wondering why in this line of the gaussian diffusion condition score you are multiplying the right side by zero: https://github.com/JuliaWolleb/Diffusion-based-Segmentation/blob/676f214035e90edd0357f51feab45841e4aefcfb/guided_diffusion/gaussian_diffusion.py#L387 In...

bennymi

Hello there, If the testing set does not have any segmentation mask (ground truth), then how are we going to calculate the Dice and IoU (Jaccard Index) of the generated...

IshaqMKhan

Hi, thank you again. I used the code to train my custom dataset pair dataset; (input image, target image). It works when I convert the dataset to grayscale, but it...

yug125lk