|
--- |
|
license: cc-by-4.0 |
|
pipeline_tag: image-to-image |
|
tags: |
|
- pytorch |
|
- super-resolution |
|
--- |
|
|
|
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xNature_realplksr_dysample) |
|
|
|
# 4xNature_realplksr_dysample |
|
Scale: 4 |
|
Architecture: [RealPLKSR with Dysample](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs) |
|
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py) |
|
|
|
Author: Philip Hofmann |
|
License: CC-BY-0.4 |
|
Purpose: Restoration |
|
Subject: Realistic |
|
Input Type: Images |
|
Release Date: 13.08.2024 |
|
|
|
Dataset: [Nature](https://github.com/Phhofm/models/releases/tag/nature_dataset) |
|
Dataset Size: 7'000 |
|
OTF (on the fly augmentations): No |
|
Pretrained Model: [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample) |
|
Iterations: 265'000 |
|
Batch Size: 8 |
|
Patch Size: 64 |
|
|
|
Description: |
|
A Dysample RealPLKSR 4x upscaling model for photographs nature (animals, plants). |
|
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). |
|
Trained with dysample, ea2fpn, ema, eco, adan_sf, mssim, perceptual, color, luma, dists, ldl and ff (see config toml file). |
|
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. |
|
|
|
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. |
|
|
|
Showcase: |
|
 |
|
 |
|
 |
|
 |
|
 |
|
|
