Giters

DeweiHu / OCT_DDPM

Application of Diffusion Probablistic Model for unsupervised OCT denoising

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Complete code

zxt-triumph opened this issue · comments

commented

First of all, thank you very much for your work, I hope you can open source the complete code, including training, testing, etc. If it is not convenient to open source, Could you send it to me privately, thank you very much.

commented
commented

@DeweiHu Thank you for your share.I am very interested in your work in paper Unsupervised Denoising of Retinal OCT with Diffusion,and if posible I hope you can share complete code or just send it to me privately so that I can learn more details.Thank you for your share,again.

commented

Hello,

Thank you for your interest! I uploaded the code I was using for model setting, pre-processing, training and testing in /src/. I am sorry that I didn't get time to clean the code. Please let me know if you need anything.

Thanks,
Dewei

commented
commented

Thanks very much for sharing the code! I just wanted to clarify one thing, which is that in trainDataset, the data loader should load noisy images (not clean images), correct? So the network can learn from noisy images of various different SNR levels and does not require any clean data at all.

commented