Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,31 @@
|
|
| 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/4xLSDIRCompact3)
|
| 10 |
+
|
| 11 |
+
# 4xLSDIRCompactN3
|
| 12 |
+
|
| 13 |
+
**Name:** 4xLSDIRCompactN3
|
| 14 |
+
**Author:** Philip Hofmann
|
| 15 |
+
**Release Date:** 11.04.2023
|
| 16 |
+
**License:** CC BY 4.0
|
| 17 |
+
**Model Architecture:** SRVGGNetCompact
|
| 18 |
+
**Scale:** 4
|
| 19 |
+
**Purpose:** Upscale good quality input photos to x4 their size
|
| 20 |
+
**Iterations:** 185'000
|
| 21 |
+
**batch_size:** Variable(1-10)
|
| 22 |
+
**HR_size:** 256
|
| 23 |
+
**Dataset:** LSDIR
|
| 24 |
+
**Dataset_size:** 84991 hr + 84991 lr
|
| 25 |
+
**OTF Training** No
|
| 26 |
+
**Pretrained_Model_G:** 4x_Compact_Pretrain.pth
|
| 27 |
+
**Description:** The original 4xLSDIRCompact a bit more trained, cannot handle degradation
|
| 28 |
+
**Total Training Time:** 32+ hours
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|