UNet adapted for SuperResolution, implemented as homework for Artificial Intelligence II at CIMAT. The model uses downscaled STL-10 patches to for training (96x96 to 48x48)
The script unetSR.py contains the class with the UNet implementation.
The notebook UnetSR.ipynb contains the training the net and an inference example using the trained weights (unet_final_1.pt).
-
Notifications
You must be signed in to change notification settings - Fork 1
villacu/UNet_SR
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
UNet adapted for SuperResolution
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published