Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
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/4xNomosUni_span_multijpg)
|
10 |
+
|
11 |
+
# 4xNomosUni_span_multijpg
|
12 |
+
|
13 |
+
Name: 4xNomosUni_span_multijpg
|
14 |
+
Author: Philip Hofmann
|
15 |
+
Release Date: 09.12.2023
|
16 |
+
License: CC BY 4.0
|
17 |
+
Network: SPAN
|
18 |
+
Scale: 4
|
19 |
+
Purpose: 4x fast universal upscaler
|
20 |
+
Iterations: 57'000
|
21 |
+
epoch: 33
|
22 |
+
batch_size: 9
|
23 |
+
HR_size: 512
|
24 |
+
Dataset: nomosuni
|
25 |
+
Number of train images: 2989
|
26 |
+
OTF Training: No
|
27 |
+
Pretrained_Model_G: spanx4_ch48.pth
|
28 |
+
|
29 |
+
Description:
|
30 |
+
4x fast universal upscaler pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos).
|
31 |
+
|
32 |
+
Slow Pics examples (put otf_weak also in there for comparison):
|
33 |
+
[digital_art](https://slow.pics/c/vqIsFsDI)
|
34 |
+
[ani_bokeh](https://slow.pics/c/bConWVoE)
|
35 |
+
[face](https://slow.pics/c/SJOJ8aNJ)
|
36 |
+
![digital_art_comp](https://github.com/Phhofm/models/assets/14755670/1cf12f97-8c7a-47b8-b4c2-0f2e53d3a330)
|
37 |
+
![face_comp](https://github.com/Phhofm/models/assets/14755670/edd641e9-37e7-445b-ae71-db53dea96b25)
|
38 |
+
![ani_bokeh_comp](https://github.com/Phhofm/models/assets/14755670/b9a30029-2c22-44f8-a353-9723aec0c41f)
|