Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,25 @@
|
|
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/2xHFA2kAVCCompact)
|
6 |
+
|
7 |
+
Name: 2xHFA2kAVCCompact
|
8 |
+
Author: Philip Hofmann
|
9 |
+
Release Date: 18.06.2023
|
10 |
+
License: CC BY 4.0
|
11 |
+
Network: SRVGGNet
|
12 |
+
Scale: 2
|
13 |
+
Purpose: Fast 2x anime upscaling model that handles AVC (h264) degradation
|
14 |
+
Iterations: 111,000
|
15 |
+
batch_size: 4
|
16 |
+
HR_size: 256
|
17 |
+
Dataset: HFA2k_h264
|
18 |
+
Number of train images: 2568
|
19 |
+
OTF Training: No
|
20 |
+
Pretrained_Model_G: None
|
21 |
+
|
22 |
+
Description: A 2x Compact anime upscale model that handles AVC (h264) degradation. Applied h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling on the HFA2k dataset with Kim's dataset destroyer.
|
23 |
+
|
24 |
+
![image](https://github.com/Phhofm/models/assets/14755670/7cd72469-4631-4f20-b5af-227692b1879a)
|
25 |
+
![324388155-7cd72469-4631-4f20-b5af-227692b1879a](https://github.com/Phhofm/models/assets/14755670/d641c8b4-6061-4131-9aeb-7bac0f49e1d1)
|