Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 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/4xNomos8kHAT-L_otf)
|
| 6 |
+
|
| 7 |
+
# 4xNomos8kHAT-L_otf
|
| 8 |
+
|
| 9 |
+
Name: 4xNomos8kHAT-L_otf
|
| 10 |
+
Author: Philip Hofmann
|
| 11 |
+
Release Date: 01.11.2023
|
| 12 |
+
License: CC BY 4.0
|
| 13 |
+
Network: HAT
|
| 14 |
+
Scale: 4
|
| 15 |
+
Purpose: 4x photo upscaler
|
| 16 |
+
Iterations: 220000
|
| 17 |
+
epoch: 19
|
| 18 |
+
batch_size: 4
|
| 19 |
+
HR_size: 128
|
| 20 |
+
Dataset: nomos8k
|
| 21 |
+
Number of train images: 8492
|
| 22 |
+
OTF Training: Yes
|
| 23 |
+
Training time: 60 hours on a remote P100
|
| 24 |
+
Pretrained_Model_G: HAT-L_SRx4_ImageNet-pretrain
|
| 25 |
+
|
| 26 |
+
Description:
|
| 27 |
+
4x photo upscaler trained with otf, handles some jpg compression, some blur and some noise.
|
| 28 |
+
|
| 29 |
+
|