DISAPPEARED13
DISAPPEARED13
Hi, there. I am sticking for a more stable training also strengthen D for clearer synthesis. Would it work for just add GP in PatchGAN? Thanks.
I found that's because I use the resnet, which will reduce the resolution of the z-axis from 16(original) to 1. That's funny...
edit the resnet type from ***_os16 to ***_os8 can solve this problem, but let's see what's going on.
Hi there, I've met some new issue, that is, to reduce the times of down sampling in z-axis, I have to change some kernel size and stride and padding when...
I solved this problem with adding some slices in the front and back of the volume... I thought that my data got something wrong or I gave the wrong input,...
I face the same problem when I am training a Cyclegan, with torch.sigmoid(D(fake_img)) and GANloss: BCELoss() and finally My G fell into mode failure... Now I try BCELossWithLogits() see what...
Hi, there, what if my background class is 0, but others is from 1 to 13? How to ignore the background prediction? because at the test part, I got the...
> > Hi, there, what if my background class is 0, but others is from 1 to 13? How to ignore the background prediction? because at the test part, I...
It seems that the input channel in model definition is 1, single modality. I'm curious if this self-supervised pre-training based weights can identify information about other modalities(for example T1/T2/Flair/... in...
I am confused that I have met the same problem, even the gradient didn't update. The first iteration, I got the all-zero probability map, means that each class including the...