---
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/4xSSDIRDAT)

# 4xSSDIRDAT

Name: 4xSSDIRDAT  
Author: Philip Hofmann  
Release: 10.09.2023  
License: CC BY 4.0  
Network: DAT  
Scale: 4  
Purpose: 4x photo upscaler  
Iterations: 110000  
epoch: 40  
batch_size: 4  
HR_size: 128  
Dataset: SSDIR_Sharp  
Number of train images: 10000  
OTF Training: Yes  
Pretrained_Model_G: 4xFaceUpSharpDAT  

Description: 4x photo upscaler on the SSDIR_Sharp dataset, trained with otf for jpg, resize and small blur. (this might have trouble handling bokeh effect because of dataset, also should probably have used non-sharp version of dataset)

![4xSSDIRDAT](https://github.com/Phhofm/models/assets/14755670/50bdcd4c-f0e5-4be8-932a-f0a162facc7e)
![4xSSDIRDAT](https://github.com/Phhofm/models/assets/14755670/91b80d8e-8f49-4ec6-9fbe-e18c617ae204)