Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,54 @@
|
|
| 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/2xHFA2kCompact)
|
| 6 |
+
|
| 7 |
+
Name: 2xHFA2kCompact
|
| 8 |
+
Author: Philip Hofmann
|
| 9 |
+
Release Date: 18.04.2023
|
| 10 |
+
License: CC BY 4.0
|
| 11 |
+
Network: SRVGGNetCompact, with parameters: 600,652
|
| 12 |
+
Scale: 2
|
| 13 |
+
Purpose: A compact anime 2x upscaling model based on musl's HFA2k dataset
|
| 14 |
+
|
| 15 |
+
Iterations: 93,000
|
| 16 |
+
batch_size: 12
|
| 17 |
+
HR_size: 384
|
| 18 |
+
Epoch: 207 (require iter number per epoch: 214)
|
| 19 |
+
Dataset: HFA2k
|
| 20 |
+
Number of train images: 2568
|
| 21 |
+
OTF Training: Yes
|
| 22 |
+
Pretrained_Model_G: 4x_Compact_Pretrain
|
| 23 |
+
Training time: 24h+
|
| 24 |
+
|
| 25 |
+
Description: Compact 2x anime upscaler with otf compression and blur. The '2xHFA2kCompact.pth' (4.6 MB) is the original trained model file, the other model files are conversions using chaiNNer. Trained on musl's latest dataset release for Anime SISR, which has been extracted from modern anime films, where the selection criteria was high SNR, no DOF and high frequency information.
|
| 26 |
+
|
| 27 |
+
Examples: https://imgsli.com/MTcxNjA4
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|