Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xNomosUni_rgt_multijpg)
|
| 6 |
+
|
| 7 |
+
# 4xNomosUni_rgt_multijpg
|
| 8 |
+
|
| 9 |
+
Name: 4xNomosUni_rgt_multijpg
|
| 10 |
+
License: CC BY 4.0
|
| 11 |
+
Author: Philip Hofmann
|
| 12 |
+
Network: RGT
|
| 13 |
+
Scale: 4
|
| 14 |
+
Release Date: 20.02.2024
|
| 15 |
+
Purpose: 4x universal DoF preserving upscaler
|
| 16 |
+
Iterations: 100'000
|
| 17 |
+
epoch: 79
|
| 18 |
+
batch_size: 12
|
| 19 |
+
HR_size: 128
|
| 20 |
+
Dataset: nomosuni
|
| 21 |
+
Number of train images: 2989
|
| 22 |
+
OTF Training: No
|
| 23 |
+
Pretrained_Model_G: RGT_x4
|
| 24 |
+
|
| 25 |
+
Description:
|
| 26 |
+
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 and color losses.
|
| 27 |
+
Similiar to the 4xNomosUni_rgt_s_multijpg model I released, with same dataset, this is a full RGT model in comparison.
|
| 28 |
+
|
| 29 |
+
6 Examples (To check JPG compression handling see Example Nr.4, to check Depth of Field handlin see Example Nr.1 & Nr.6):
|
| 30 |
+
[Slowpics](https://slow.pics/s/iMuE3vE5)
|
| 31 |
+
|
| 32 |
+
|