Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
| 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 |
+
- restoration
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xDeJPG)
|
| 10 |
+
|
| 11 |
+
# 1xDeJPG_OmniSR
|
| 12 |
+
|
| 13 |
+
Name: 1xDeJPG_OmniSR
|
| 14 |
+
Author: Philip Hofmann
|
| 15 |
+
Release Date: 02.08.2023
|
| 16 |
+
License: CC BY 4.0
|
| 17 |
+
Network: OmniSR
|
| 18 |
+
Scale: 1
|
| 19 |
+
Purpose: A 1xDeJPG model
|
| 20 |
+
Iterations: 439,000
|
| 21 |
+
batch_size: 4
|
| 22 |
+
HR_size: 32
|
| 23 |
+
Dataset: Nomos8k_sfw (processed with kim's datasetdestroyer - 2x jpg compression added)
|
| 24 |
+
Number of train images: 6118
|
| 25 |
+
OTF Training: No
|
| 26 |
+
Pretrained_Model_G: None
|
| 27 |
+
|
| 28 |
+
Description: 1xDeJPG model, meant to remove jpg artifacts. First compression round on the training dataset was 40-95, second round was 80-100.
|