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
Get Strange results when training a X3 upsacle ESRGAN model #74
Comments
@JunbinWang checkout https://distill.pub/2016/deconv-checkerboard/ |
Hi @slee5777, Thanks for your reply! So you suggest that this is caused by wrong Upsampling factors? Maybe I should not upscale the LR image to x3 ? |
This is pretty cool. I did struggle to get rid of those artefacts. |
Yeah,I check your code again carefully today. We did apply pixel shuffle in the RRDN model. |
I mean, I could easily be wrong and that could also be an issue with the pixel shuffling operation. You should try to experiment with strides and kernel sizes. Let me know how it goes. |
How do you determine the weight of these three parameters? What do the three of them stand for? How to adjust to achieve optimal? loss_weights = {
|
Dear all,
When I try to train a ArtefactCancelling ESRGAN model, I get some result images with strange patterns.
I put some sample images here:
I first train the model with only mae loss as the script below.
Then I train the model with the following configuration :
Can somebody give me some hints about what may cause the unpleased image patterns?
Best Regards,
Even
The text was updated successfully, but these errors were encountered: