Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,41 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
pipeline_tag: image-to-image
|
| 4 |
+
tags:
|
| 5 |
+
- pytorch
|
| 6 |
+
- super-resolution
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xHFA2k_ludvae_realplksr_dysample)
|
| 10 |
+
|
| 11 |
+
# 4xLSDIRCompactR
|
| 12 |
+
|
| 13 |
+
Name: 4xLSDIRCompactR
|
| 14 |
+
Author: Philip Hofmann
|
| 15 |
+
Release Date: 17.03.2023
|
| 16 |
+
License: CC BY 4.0
|
| 17 |
+
Network: SRVGGNetCompact
|
| 18 |
+
Scale: 4
|
| 19 |
+
Purpose: 4x photo uspcaler that handles jpg compression, noise and slight
|
| 20 |
+
|
| 21 |
+
Iterations: 130000
|
| 22 |
+
batch_size: Variable(1-5)
|
| 23 |
+
HR_size: 256
|
| 24 |
+
Dataset: LSDIR
|
| 25 |
+
Dataset_size: 84991
|
| 26 |
+
OTF Training No
|
| 27 |
+
Pretrained_Model_G: 4xLSDIRCompact.pth
|
| 28 |
+
|
| 29 |
+
Description: Extending my last 4xLSDIRCompact model to Real-ESRGAN, meaning trained on synthetic data instead to handle more kinds of degradations, it should be able to handle compression, noise, and slight blur.
|
| 30 |
+
|
| 31 |
+
---
|
| 32 |
+
|
| 33 |
+
Here is a comparison to show that 4xLSDIRCompact cannot handle compression artifacts, and that these two models will produce better output for that specific scenario. These models are not ‘better’ than the previous one, they are just meant to handle a different use case: https://imgsli.com/MTYyODY3
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|