---
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/4xNomos8k_atd_jpg)


# 4xNomos8k_atd_jpg

Name: 4xNomos8k_atd_jpg  
License: CC BY 4.0  
Author: Philip Hofmann  
Network: [ATD](https://github.com/LabShuHangGU/Adaptive-Token-Dictionary)  
Scale: 4  
Release Date: 22.03.2024  
Purpose: 4x photo upscaler, handles jpg compression  
Iterations: 240'000  
epoch: 152  
batch_size: 6, 3  
HR_size: 128, 192  
Dataset: nomos8k  
Number of train images: 8492  
OTF Training: Yes  
Pretrained_Model_G: 003_ATD_SRx4_finetune  

Description:  
4x photo upscaler which handles jpg compression. This model will preserve noise. Trained on the very recently released (~2 weeks ago) Adaptive-Token-Dictionary network.     

Training details:   
AdamW optimizer with U-Net SN discriminator and BFloat16.  
Degraded with otf jpg compression down to 40, re-compression down to 40, together with resizes and the blur kernels.    
Losses: PixelLoss using CHC (Clipped Huber with Cosine Similarity Loss), PerceptualLoss using Huber, GANLoss, [LDL](https://github.com/csjliang/LDL) using Huber, YCbCr Color Loss (bt601) and Luma Loss (CIE XYZ) on [neosr](https://github.com/muslll/neosr).

7 Examples:
[Slowpics](https://slow.pics/s/uwnoI435)

![4xNomos8k_atd_jpg_example1](https://github.com/Phhofm/models/assets/14755670/77bdf964-8c72-47b7-b1b2-4b882e8b1d95)
![4xNomos8k_atd_jpg_example2](https://github.com/Phhofm/models/assets/14755670/85ebcc73-8c28-482d-b3a6-dd0a56a1b17c)
![4xNomos8k_atd_jpg_example3](https://github.com/Phhofm/models/assets/14755670/03a30404-a428-4853-8623-c59e57518f66)
![4xNomos8k_atd_jpg_example4](https://github.com/Phhofm/models/assets/14755670/4a598d9e-b323-4929-9d44-a4100dda2abb)