| | --- |
| | 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/4xNomos8kSC) |
| |
|
| | # 4xNomos8kSC |
| |
|
| | Name: 4xNomos8kSC |
| | Author: Philip Hofmann |
| | Release Date: 10.05.2023 |
| | License: CC BY 4.0 |
| | Network: RRDBNet |
| | Scale: 4 |
| | Purpose: A 4x photo ESRGAN upscaling model, handles jpg compression and slight blur |
| | Iterations: 85,000 |
| | batch_size: 10 |
| | HR_size: 256 |
| | Epoch: 137 |
| | Dataset: Nomos8k_sfw |
| | Number of train images: 6118 |
| | OTF Training: Yes |
| | Pretrained_Model_G: RealESRGAN_x4plus.pth |
| | Training time: 36h on a P100 GPU |
| |
|
| | Description: 4x photo ESRGAN upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr. |
| | |
| | Examples: https://imgsli.com/MTc3MzU1 |
| | |
| |  |
| |  |
| |  |
| | |
