Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,37 @@
|
|
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/4xNomos8kSCSRFormer)
|
10 |
+
|
11 |
+
# 4xNomos8kSCSRFormer
|
12 |
+
|
13 |
+
Name: 4xNomos8kSCSRFormer
|
14 |
+
Author: Philip Hofmann
|
15 |
+
Release Date: 26.06.2023
|
16 |
+
License: CC BY 4.0
|
17 |
+
Network: SRFormer
|
18 |
+
Scale: 4
|
19 |
+
Purpose: A photo 4x upscaling model based on musl's Nomos8k_sfw dataset for realistic sr
|
20 |
+
Iterations: 115,000
|
21 |
+
batch_size: 4
|
22 |
+
HR_size: 256
|
23 |
+
Dataset: Nomos8k_sfw
|
24 |
+
Number of train images: 6118
|
25 |
+
OTF Training: Yes
|
26 |
+
Pretrained_Model_G: SRFormer_SRx4_DF2K.pth
|
27 |
+
|
28 |
+
Description: 4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr
|
29 |
+
|
30 |
+
Examples
|
31 |
+
Imgsli Example 1: https://imgsli.com/MTg4Mjc5
|
32 |
+
Imgsli Example 2: https://imgsli.com/MTg4Mjgw
|
33 |
+
|
34 |
+
![Example1](https://github.com/Phhofm/models/assets/14755670/1f4f1a11-f5fa-45ca-931a-f2d477993ebc)
|
35 |
+
![Example2](https://github.com/Phhofm/models/assets/14755670/0a7105b4-8605-4c2a-a813-86ebd66784ab)
|
36 |
+
![Example3](https://github.com/Phhofm/models/assets/14755670/030e8d33-c21b-4587-8f64-f23093bc289f)
|
37 |
+
![Example4](https://github.com/Phhofm/models/assets/14755670/869f473f-e243-4e28-9ddf-7ea53db23f1f)
|