Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,39 @@
|
|
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_rgt_s_multijpg)
|
10 |
+
|
11 |
+
# 4xNomosUni_rgt_s_multijpg
|
12 |
+
|
13 |
+
Name: 4xNomosUni_rgt_s_multijpg
|
14 |
+
License: CC BY 4.0
|
15 |
+
Author: Philip Hofmann
|
16 |
+
Network: RGT
|
17 |
+
Scale: 4
|
18 |
+
Release Date: 16.02.2024
|
19 |
+
Purpose: 4x universal DoF preserving upscaler
|
20 |
+
Iterations: 87'000
|
21 |
+
epoch: 68
|
22 |
+
batch_size: 12
|
23 |
+
HR_size: 128
|
24 |
+
Dataset: nomosuni
|
25 |
+
Number of train images: 2989
|
26 |
+
OTF Training: No
|
27 |
+
Pretrained_Model_G: DAT_2_x4
|
28 |
+
|
29 |
+
Description:
|
30 |
+
4x universal DoF preserving upscaler, pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos) in neosr with adamw, unet and pixel, perceptual, gan, color and ldl losses.
|
31 |
+
|
32 |
+
Examples:
|
33 |
+
[Imgsli](https://imgsli.com/MjQwNDk5)
|
34 |
+
[Slowpics](https://slow.pics/s/sIRl3w7J)
|
35 |
+
|
36 |
+
![Face_4xNomosUni_rgt_s_multijpg](https://github.com/Phhofm/models/assets/14755670/82d85217-3bd9-4629-b39a-01ec39b66330)
|
37 |
+
![Car_4xNomosUni_rgt_s_multijpg](https://github.com/Phhofm/models/assets/14755670/26c980c9-2b19-46b8-8ea2-8ff642b55440)
|
38 |
+
![Digitalart_4xNomosUni_rgt_s_multijpg](https://github.com/Phhofm/models/assets/14755670/4915f7fd-da2d-4fb2-b29a-3bd32516c008)
|
39 |
+
![SDRevolverMouse_4xNomosUni_rgt_s_multijpg](https://github.com/Phhofm/models/assets/14755670/d641c505-9efd-4fff-a284-b6ab4839f66c)
|