Closed Iceland-Leo closed 3 years ago
Strangely, I have the same problem with my own HDR dataset. Additionally, I just use OpenCV version 4.4 instead of 3, is this the reason for this problem?
Today, I replace your 5 tone mapping methods with another tone mapping method, and I am surprised to find that the training goes well. But in order to make a fair comparison and get the correct results in your paper, I still want to know why using your 5 tone mapping method can't train the model properly. Could you help me find the reasion?
Hello there,
I'm glad it works now. I'm not sure what exactly is going wrong, but it sounds like it's with the tone mapping. I haven't ran the training recently with newer versions of the libraries so that might be the problem.
In any case, maybe try to run it using a single tone mapper each time from the provided OpenCV ones. This way you might find the specific tone mapper that causes the problem.
Best, Demetris
OKay, I will try it.
Experiments show that different version of OpenCV is the key reason. I recommend that you can emphasize this issue in the "README.md" so that others do not encounter the same problem. Thank you very much for your prompt reply.
Thanks for investigating this! I will add a note on the readme.
Hi, I use the datasets provided by a CVPR2020 paper "Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline" to train ExpandNet, but the loss value never decreases, and the generated image is all black image. I am sure that I haven't changed anything except the training data. Why is that? Is it the datasets that's causing the problem?