|
--- |
|
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/4xNomos8kDAT) |
|
|
|
# 4xNomos8kDAT |
|
|
|
Name: 4xNomos8kDAT |
|
Author: Philip Hofmann |
|
Release Date: 13.08.2023 |
|
License: CC BY 4.0 |
|
Network: [DAT](https://github.com/zhengchen1999/DAT) |
|
Architecture Option: DAT |
|
Scale: 4 |
|
Purpose: 4x photo upscaling model for realistic sr |
|
Iterations: 110000 |
|
epoch: 71 |
|
batch_size: 4 |
|
HR_size: 128 |
|
Dataset: [Nomos8k_sfw](https://discord.com/channels/547949405949657098/905446120333930566/1037853129112289321) |
|
Number of train images: 6118 |
|
OTF Training: Yes |
|
Pretrained_Model_G: [DAT_x4.pth](https://drive.google.com/file/d/1pEhXmg--IWHaZOwHUFdh7TEJqt2qeuYg) |
|
|
|
Description: 4x photo upscaler with otf jpg compression, blur and resize, trained on musl's Nomos8k_sfw dataset for realisic sr, this time based on the DAT arch, as a finetune on the official 4x DAT model. |
|
|
|
Examples: |
|
[Imgsli1](https://imgsli.com/MTk4Mjg1) (generated with onnx file) |
|
[Imgsli2](https://imgsli.com/MTk4Mjg2) (generated with onnx file) |
|
[Imgsli](https://imgsli.com/MTk4Mjk5) (generated with testscript of dat repo on the three test images in dataset/single with pth file) |
|
|
|
 |
|
 |
|
 |
|
|
