zejinwang / Blind2Unblind

This is an official implementation of the CVPR2022 paper "Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots".
https://arxiv.org/abs/2203.06967
118 stars 13 forks source link

关于ValidationGtBlocksRaw.mat和ValidationNoisyBlocksRaw.mat问题。 #20

Open tianshukai99 opened 1 year ago

tianshukai99 commented 1 year ago

尊敬的作者先生 您好!!! 我想关于ValidationGtBlocksRaw.mat和ValidationNoisyBlocksRaw.mat两个文件问您一些问题。 问题1:这两个文件我是需要根据我自己的数据集制作,还是直接从您给出的那个网址进行下载即可? 问题2:当我运行Train on SIDD raw-RGB Medium dataset命令时,报错 TypeError: Expecting miMATRIX type here, got 16843009,请问这是什么问题? 问题3:我现在有RGB的红外图像,我用Train on SIDD raw-RGB Medium dataset这个训练命令可以吗?

如果方便的话,请您把您的联系方式给我一个可以吗?

希望当您看到我的问题,辛苦给出一些解答,学生定不胜感激!!!

zejinwang commented 1 year ago

For RGB infrared data, you can train with https://github.com/zejinwang/Blind2Unblind/blob/main/train_b2u.py. When loading data, make sure to normalize it to between 0 and 1. Thanks for your attention. Please directly open issues on GitHub. Responses are typically prompt.