Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,44 @@
|
|
| 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/4xNature_realplksr_dysample)
|
| 10 |
+
|
| 11 |
+
# 4xNature_realplksr_dysample
|
| 12 |
+
Scale: 4
|
| 13 |
+
Architecture: [RealPLKSR with Dysample](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)
|
| 14 |
+
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)
|
| 15 |
+
|
| 16 |
+
Author: Philip Hofmann
|
| 17 |
+
License: CC-BY-0.4
|
| 18 |
+
Purpose: Restoration
|
| 19 |
+
Subject: Realistic
|
| 20 |
+
Input Type: Images
|
| 21 |
+
Release Date: 13.08.2024
|
| 22 |
+
|
| 23 |
+
Dataset: [Nature](https://github.com/Phhofm/models/releases/tag/nature_dataset)
|
| 24 |
+
Dataset Size: 7'000
|
| 25 |
+
OTF (on the fly augmentations): No
|
| 26 |
+
Pretrained Model: [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample)
|
| 27 |
+
Iterations: 265'000
|
| 28 |
+
Batch Size: 8
|
| 29 |
+
Patch Size: 64
|
| 30 |
+
|
| 31 |
+
Description:
|
| 32 |
+
A Dysample RealPLKSR 4x upscaling model for photographs nature (animals, plants).
|
| 33 |
+
LR prepared with down_up, linear, cubic_mitchell, lanczos, gauss and box scaling with some gaussian blur and jpg compression down to 75 (as released with my dataset, the LRx4 folder).
|
| 34 |
+
Trained with dysample, ea2fpn, ema, eco, adan_sf, mssim, perceptual, color, luma, dists, ldl and ff (see config toml file).
|
| 35 |
+
Based on my [Nature Dataset](https://github.com/Phhofm/models/releases/tag/nature_dataset) which is a curated version of the [iNaturalist 2017 Dataset](https://github.com/visipedia/inat_comp/blob/master/2017/README.md) for the purpose of training single image super resolution models.
|
| 36 |
+
|
| 37 |
+
Use the [4xNature_realplksr_dysample.pth](https://github.com/Phhofm/models/releases/download/4xNature_realplksr_dysample/4xNature_realplksr_dysample.pth) file for inference. Also provided is a static onnx conversion with 3 256 256. Config, state, and net_d files are additionally provided for trainers, to maybe create an improved version 2 of this model or to train a similiar model from this state.
|
| 38 |
+
|
| 39 |
+
Showcase:
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|