LIR-for-Unsupervised-IR

LIR-for-Unsupervised-IR copied to clipboard

The issue in the PascalVoc.py

1

As your attempt, you want to divide the pascalvoc dataset into 4, and this .py file is just for pascalvoc dataset. But in your code : def splitlist(folder, trainfolder1, trainfolder2,...

xiaoachen98

About the source and placement of the data set

4

Does the clean data set come from the VOC data set? So do you need to search for noise data by yourself? Where is the noise data set used by...

haolin512900

Hi, I tried to apply it in my own CT low-dose data, but it didn't work well. The yaml file I use is 'the unit_noise2clear-poisson.yaml'. Is the right parameters you use in the low-dose CT?

2

chris1992212

CaptainEven

Do you have any pretrained model?

1

I just test some effects of model, so can you offer your pretrained model?

xuyanging

About KL Loss

4

The work is interesting! However, in your paper, you only add a KL divergence loss to regularize the distribution of the noise code, while you add KL loss to all...

qibao77

关于训练过程

2

您好，能给一个更详细的训练过程吗？就是每次该运行哪些.py文件

sibangde

About test.py?

1

Hello, I want to ask what is '/mnt/B290B95290B91E33/Dual_UNIT/outputs/unit_noise2clear-bn-Deblur/checkpoints/gen_00300000.pt' in test.py

Zruto

in dis_update(self, x_a, x_b, hyperparameters): the content adversial codes are , out_a = self.dis_content(h_a) out_b = self.dis_content(h_b) why not use h_a.detach() and h_b.detach() to avoid the update in the parameters...

laulampaul

raywzy