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 |
+
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/4xNomos2_hq_drct-l)
|
| 10 |
+
|
| 11 |
+
# 4xNomos2_hq_dat2
|
| 12 |
+
Scale: 4
|
| 13 |
+
Architecture: [DAT](https://github.com/zhengchen1999/dat)
|
| 14 |
+
Architecture Option: [dat2](https://github.com/muslll/neosr/blob/5fba7f162d36052010169e6517dec3b406c569ab/neosr/archs/dat_arch.py#L1111)
|
| 15 |
+
|
| 16 |
+
Author: Philip Hofmann
|
| 17 |
+
License: CC-BY-0.4
|
| 18 |
+
Purpose: Upscaler
|
| 19 |
+
Subject: Photography
|
| 20 |
+
Input Type: Images
|
| 21 |
+
Release Date: 29.08.2024
|
| 22 |
+
|
| 23 |
+
Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)
|
| 24 |
+
Dataset Size: 6000
|
| 25 |
+
OTF (on the fly augmentations): No
|
| 26 |
+
Pretrained Model: DAT_2_x4
|
| 27 |
+
Iterations: 140'000
|
| 28 |
+
Batch Size: 4
|
| 29 |
+
Patch Size: 48
|
| 30 |
+
|
| 31 |
+
Description:
|
| 32 |
+
A dat2 4x upscaling model, similiar to the [4xNomos2_hq_mosr](https://github.com/Phhofm/models/releases/tag/4xNomos2_hq_mosr) model, trained and for usage on non-degraded input to give good quality output.
|
| 33 |
+
|
| 34 |
+
I scored 7 validation outputs of each of the 21 checkpoints (10k-210k) of this model training with 68 metrics.
|
| 35 |
+
[The metric scores can be found in this google sheet](https://docs.google.com/spreadsheets/d/1NL-by7WvZyDMHj5XN8UeDALVSSwH70IKvwV65ATWqrA/edit?usp=sharing).
|
| 36 |
+
The corresponding image files for this scoring can be [found here](https://drive.google.com/file/d/1ZTp9fBMeawftNqzg4RN9_zIvHtul5jVc/view?usp=sharing)
|
| 37 |
+
Screenshot of the google sheet:
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
Release checkpoint has been selected by looking at the scores, manually inspecting, and then getting responses on discord which chose B to this quick visual test, A B or C, which denote different checkpoints: https://slow.pics/c/8Akzj6rR
|
| 41 |
+
|
| 42 |
+
Checkpoint B is 140k which is 4xNomos2_hq_dat2. But I added checkpoint A (4xNomos2_hq_dat2_150000) and checkpoint C (4xNomos2_hq_dat2_10000) model files additionally here if people want to try them out).
|
| 43 |
+
|
| 44 |
+
## Model Showcase:
|
| 45 |
+
[Slowpics](https://slow.pics/c/yuue9WpF)
|
| 46 |
+
|
| 47 |
+
(Click on image for better view)
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|