-
Notifications
You must be signed in to change notification settings - Fork 226
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
About Rate Distortion Loss #199
Comments
|
Thank you for the answer, but I'm still a bit confused with the different formula for the final loss term. In the custom training documentation, it's defined as: While in the RateDistortionClass, it's defined as: Why is the |
It's just a scaling constant. It has no tangible effect, as long as Why 255? An 8-bit pixel has intensities in the interval where It's not necessary to include |
Ah, I see. Thank you for the explanation. |
Hello, thank you for the work, I'd like to ask about the different formula of the Rate Distortion Loss from your custom training documentation and from your RateDistortionLoss class.
On your custom training documentation, the Rate Distortion Loss is defined as:
While on your RateDistortionLoss class, which is used in your examples/train.py, it is:
I also notice that there's a difference in the bpp_loss calculation. In the RateDistortionClass, you sum all the bpp_loss. I also want to know why is this the case, are you summing all the bpp_loss across all the batches?
I'm wondering which loss is better to use? And is there paper that I can refer to regarding this? Thank you very much.
The text was updated successfully, but these errors were encountered: