MedSegDiff

MedSegDiff copied to clipboard

Training with different image size

2

Training with image size = 128 and ISIC dataset fails. Failing occurs when values are going through FFParser.  I assume this is related to hardcoded values in the instantiation...

elrandar

how to change the code to run multiclass segmentation task

2

please help

TMullerSG

Hi, when i changed batch size larger than 1, i get error in gaussian_diffusion.py, assert t.shape == (B,). and you mentioned can use num_samples to control number of test images,...

TMullerSG

error in create_argparser

1

defaults.update({k: v for k, v in model_and_diffusion_defaults().items() if k not in defaults}) Hi, i believe this is what you want to have, otherwise the value will be overwriten by those...

TMullerSG

Hello, I run scripts/ segmentation_train.py on my own datasets , and I meet the problem: RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one....

ValeriaLiu

Hi, It is an excellent project to share with. I have a question when running the program. Is the number of steps set to 1000 during training and use only...

CaviarLover

I have a question regarding loss calculation: for training ``loss = (losses["loss"] * weights + losses['loss_cal'] * 10).mean()`` is used. Why do you weigh the direct prediction of the ground...

majasomething