hdrnet_legacy icon indicating copy to clipboard operation
hdrnet_legacy copied to clipboard

Published 20 hours ago • verified publisher icon mgharbi

How to prepare tfrecords for training on HDR+?

Open Awcrr opened this issue 6 years ago • 4 comments

Hi @mgharbi,

Thank you for the code and those pre-trained models. It's a great piece of work!

Recently, I've tried to reproduce the training of HDRNet on HDR+. However, I could only reach a PSNR ~21dB. I think the problem is in data preprocessing since I didn't change any of the other code. I just used ImageFilesDataPipeline instead of HDRpDataPipeline.

For the data preprocessing, I transformed raw images into jpg using "dcraw -6 -w -g 1 1" and "convert". I noticed that you used prepared tfrecords for training. Would you mind sharing your code for preparing those records? or could you please tell me what might be wrong with my data preprocessing?

Any feedback is highly appreciated.

Awcrr avatar Apr 03 '18 01:04 Awcrr

I have the same problem with you.Do you solve it

wzl2611 avatar Apr 10 '18 13:04 wzl2611

@wzl2611 haven't yet. I'm trying to tune the hyper-parameters myself based on my pre-processing.

Awcrr avatar Apr 16 '18 01:04 Awcrr

@Awcrr I think you can refer to this blog :https://blog.csdn.net/csuzhaoqinghui/article/details/51377941. Can you leave your QQ number, we communicate with each other

wzl2611 avatar Apr 16 '18 03:04 wzl2611

@Awcrr the author said :The pre-trained HDR+ model expects as input a specially formatted 16-bit linear input. In summary, starting from Bayer RAW:

Subtract black level. Apply white balance channel gains. Demosaic to RGB. Apply lens shading correction (aka vignetting correction).

I do not quite understand so What is really the format of the 16-bit linear input?

wzl2611 avatar Apr 16 '18 03:04 wzl2611