Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: keras
|
| 4 |
+
tags:
|
| 5 |
+
- keras
|
| 6 |
+
- kaggle
|
| 7 |
+
- mirnet
|
| 8 |
+
---
|
| 9 |
+
# MIRNet
|
| 10 |
+
|
| 11 |
+
[](https://share.streamlit.io/soumik12345/mirnet/app.py)
|
| 12 |
+
|
| 13 |
+
Tensorflow implementation of the MIRNet architecture as proposed by [Learning Enriched Features for Real Image
|
| 14 |
+
Restoration and Enhancement](https://arxiv.org/pdf/2003.06792v2.pdf).
|
| 15 |
+
|
| 16 |
+
**Lanuch Notebooks:** [](https://mybinder.org/v2/gh/soumik12345/MIRNet/HEAD)
|
| 17 |
+
|
| 18 |
+
**Wandb Logs:** [https://wandb.ai/19soumik-rakshit96/mirnet](https://wandb.ai/19soumik-rakshit96/mirnet)
|
| 19 |
+
|
| 20 |
+
**Blog Post:** [https://keras.io/examples/vision/mirnet/](https://keras.io/examples/vision/mirnet/)
|
| 21 |
+
|
| 22 |
+
**TFLite Variant of MIRNet:** [https://github.com/sayakpaul/MIRNet-TFLite](https://github.com/sayakpaul/MIRNet-TFLite).
|
| 23 |
+
|
| 24 |
+
**TFLite Models on Tensorflow Hub:** [https://tfhub.dev/sayakpaul/lite-model/mirnet-fixed/dr/1](https://tfhub.dev/sayakpaul/lite-model/mirnet-fixed/dr/1).
|
| 25 |
+
|
| 26 |
+
**Tensorflow JS Variant of MIRNet:** [https://github.com/Rishit-dagli/MIRNet-TFJS](https://github.com/Rishit-dagli/MIRNet-TFJS).
|
| 27 |
+
|
| 28 |
+

|
| 29 |
+
|
| 30 |
+

|
| 31 |
+
|
| 32 |
+
## Pre-trained Weights
|
| 33 |
+
|
| 34 |
+
- **Trained on 128x128 patches:** [https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing](https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing)
|
| 35 |
+
|
| 36 |
+
- **Trained on 256x256 patches:** [https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing](https://drive.google.com/file/d/1sUlRD5MTRKKGxtqyYDpTv7T3jOW6aVAL/view?usp=sharing)
|
| 37 |
+
|
| 38 |
+
## Citation
|
| 39 |
+
|
| 40 |
+
```
|
| 41 |
+
@misc{
|
| 42 |
+
2003.06792,
|
| 43 |
+
Author = {Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao},
|
| 44 |
+
Title = {Learning Enriched Features for Real Image Restoration and Enhancement},
|
| 45 |
+
Year = {2020},
|
| 46 |
+
Eprint = {arXiv:2003.06792},
|
| 47 |
+
}
|
| 48 |
+
```
|