Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,36 @@
|
|
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/4xNomos8kSC)
|
10 |
+
|
11 |
+
# 4xNomos8kSC
|
12 |
+
|
13 |
+
Name: 4xNomos8kSC
|
14 |
+
Author: Philip Hofmann
|
15 |
+
Release Date: 10.05.2023
|
16 |
+
License: CC BY 4.0
|
17 |
+
Network: RRDBNet
|
18 |
+
Scale: 4
|
19 |
+
Purpose: A 4x photo ESRGAN upscaling model, handles jpg compression and slight blur
|
20 |
+
Iterations: 85,000
|
21 |
+
batch_size: 10
|
22 |
+
HR_size: 256
|
23 |
+
Epoch: 137
|
24 |
+
Dataset: Nomos8k_sfw
|
25 |
+
Number of train images: 6118
|
26 |
+
OTF Training: Yes
|
27 |
+
Pretrained_Model_G: RealESRGAN_x4plus.pth
|
28 |
+
Training time: 36h on a P100 GPU
|
29 |
+
|
30 |
+
Description: 4x photo ESRGAN upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr.
|
31 |
+
|
32 |
+
Examples: https://imgsli.com/MTc3MzU1
|
33 |
+
|
34 |
+
![Example1](https://github.com/Phhofm/models/assets/14755670/0bdbe964-96e9-408e-ac1b-e9d8f57a2739)
|
35 |
+
![Example2](https://github.com/Phhofm/models/assets/14755670/6aef8682-755c-44d0-85d2-9a7def948182)
|
36 |
+
![Example3](https://github.com/Phhofm/models/assets/14755670/00b1df1d-2618-47fb-8e99-f3d11e58d222)
|