galaxies99 / deephdr-pytorch Goto Github PK

Hi, thank you for your effort and this great work!

I have some questions about tone mapping and checkpoints.
Do you think we can implement a tone mapping function for this model to automize post process instead of using another application?

Additionally, I trained model for 50 epoch and model have not been saving any checkpoint until now. I'm working on Google Colab so, if there is a way that making possible to get more checkpoints it would be great.

If do you have any idea about this questions, I'd be happy to hear that for further development.
Thanks in advance!

Hello,

Would you be able to include a pretrained model in this repo?
It will help the community a lot.

Thank you

Thank you very much for your code. When you use HDRpatches.py for training, do you have the problem of image size misalignment?

Hello!
Thank you very much for this repo!

It seems that the dataset download link (https://www.robots.ox.ac.uk/~szwu/storage/hdr/kalantari_dataset.zip) is broken at the moment.
I tried to use the datasets from https://cseweb.ucsd.edu//~viscomp/projects/SIG17HDR/ but they have different structure.
For example, Training/001 has three .tif files, exposure.txt, and HDRImg.hdr.
So I am not sure what I should pass as inputs to KlantariDataset() from dataset/HDRpatches.py
I am especially unsure what values should ref_name, input_exp_name, and ref_exp_name take.

Any help will be highly appreciated. Thank you

Regarding LDR2HDR inHDRutils.py, why do we need to multiply 2 and then subtract 1?