Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,47 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
pipeline_tag: image-to-image
|
| 4 |
+
tags:
|
| 5 |
+
- pytorch
|
| 6 |
+
- super-resolution
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xRealWebPhoto_v4_drct-l)
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## 4xRealWebPhoto_v4_drct-l
|
| 13 |
+
|
| 14 |
+
**Scale:** 4
|
| 15 |
+
**Architecture:** [DRCT](https://github.com/ming053l/DRCT)
|
| 16 |
+
**Architecture Option:** [DRCT-L](https://github.com/ming053l/DRCT/blob/8c13e63135f494913cd504c073e41ef52250d1d4/options/train/train_DRCT-L_SRx4_finetune_from_ImageNet_pretrain.yml#L56)
|
| 17 |
+
|
| 18 |
+
**Author:** Philip Hofmann
|
| 19 |
+
**License:** CC-BY-0.4
|
| 20 |
+
**Purpose:** Restoration
|
| 21 |
+
**Subject:** Realistic, Photography
|
| 22 |
+
**Input Type:** Images
|
| 23 |
+
**Release Date:** 02.05.2024
|
| 24 |
+
|
| 25 |
+
**Dataset:** 4xRealWebPhoto_v4
|
| 26 |
+
**Dataset Size:** 8492
|
| 27 |
+
**OTF (on the fly augmentations):** No
|
| 28 |
+
**Pretrained Model:** 4xmssim_drct-l_pretrain
|
| 29 |
+
**Iterations:** 260'000
|
| 30 |
+
**Batch Size:** 6,4
|
| 31 |
+
**GT Size:** 128,192
|
| 32 |
+
|
| 33 |
+
**Description:** The first real-world drct model, so I am releasing it, or at least my try at it, maybe others will be able to get better results than me, I think I'd recommend my [4xRealWebPhoto_v3_atd](https://github.com/Phhofm/models/releases/tag/4xRealWebPhoto_v3_atd) model over this one if a real-world model for upscaling photos downloaded from the web is desired.
|
| 34 |
+
This model is based on my previously released drct pretrain. Used mixup, cutmix, resizemix augmentations, and mssim, perceptual, gan, dists, ldl, focalfrequency, gradvar, color and luma losses.
|
| 35 |
+
|
| 36 |
+
**Showcase:**
|
| 37 |
+
[Slow.pics](https://slow.pics/s/VOKVChT9)
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|