In, this I have implemented composite loss, employing SSIM,L1 loss, perceptual loss and M1loss.In this ,the results are not to the last ,as I tuned the model a lot of times, but the structure of model and loss can be acknowledged from here.
Results
-
Notifications
You must be signed in to change notification settings - Fork 0
m-ali-awan/super-resolution-ssimadded
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
SuperResolution using ESRGAN architecture with custom loss
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published