Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,42 @@
|
|
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/4xNomos8kSCHAT)
|
10 |
+
|
11 |
+
# 4xNomos8kSCHAT-S
|
12 |
+
|
13 |
+
Name: 4xNomos8kSCHAT-S
|
14 |
+
Author: Philip Hofmann
|
15 |
+
Release Date: 30.06.2023
|
16 |
+
License: CC BY 4.0
|
17 |
+
Network: HAT
|
18 |
+
Architecture Option: HAT-S
|
19 |
+
Scale: 4
|
20 |
+
Purpose: A photo 4x upscaling model based on musl's Nomos8k_sfw dataset for realistic sr
|
21 |
+
Iterations: 169,000
|
22 |
+
batch_size: 4
|
23 |
+
HR_size: 256
|
24 |
+
Dataset: Nomos8k_sfw
|
25 |
+
Number of train images: 6118
|
26 |
+
OTF Training: Yes
|
27 |
+
Pretrained_Model_G: HAT-S_SRx4.pth
|
28 |
+
|
29 |
+
Description: 4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr. A similiar model as above, but as an HAT-S model instead.
|
30 |
+
|
31 |
+
---
|
32 |
+
|
33 |
+
Examples
|
34 |
+
Imgsli Example 1: https://imgsli.com/MTg5MDYy
|
35 |
+
Imgsli Example 2: https://imgsli.com/MTg5MDY1
|
36 |
+
Imgsli Example 3: https://imgsli.com/MTg5MDY2
|
37 |
+
Imgsli Example 4: https://imgsli.com/MTg5MDY3
|
38 |
+
|
39 |
+
![Example1](https://github.com/Phhofm/models/assets/14755670/cf65b41a-3ab6-4857-8c75-696705cb7690)
|
40 |
+
![Example2](https://github.com/Phhofm/models/assets/14755670/b1007cba-2c15-424c-a86a-0698e2e51b8f)
|
41 |
+
![Example3](https://github.com/Phhofm/models/assets/14755670/69b684a0-fedc-4640-b24d-9411780616c2)
|
42 |
+
![Example4](https://github.com/Phhofm/models/assets/14755670/d7ca3fd0-3ff9-4da3-9791-8459c97daeb9)
|