README.md

---
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/2xEvangelion_compact)  

# 2xEvangelion_compact

Name: 2xEvangelion_compact  
License: CC BY 4.0  
Release Date: 04.02.2024 (dd/mm/yy)  
Author: Philip Hofmann  
Network: SRVGGNetCompact  
Scale: 2  
Purpose: 2x upscaler for evangelion episodes  
Iterations: 262'000  
epoch: 204  
batch_size: 12-24  
HR_size: 128-256  
Dataset: "Upscale Archive Evangelion DVD's" by pwnsweet  
Number of train images: 3174  
OTF Training: No  
Pretrained_Model_G: 2x-Compact-Pretrain  

Description:  
2x upscaler for evangelion episodes on the evangelion dataset provided by pwnsweet, which called for model trainers to train models on it.  
![Example1](https://github.com/Phhofm/models/assets/14755670/673e1104-2427-40d6-bd8b-9d7a7b225395)
![Example2](https://github.com/Phhofm/models/assets/14755670/31ec726c-85c7-4e99-817d-80ae0261e849)
![Example3](https://github.com/Phhofm/models/assets/14755670/69f95c6f-8194-4c10-ae6c-acf456eb1995)