Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# Low-Light Image Super-Resolution (HAT)
|
| 3 |
+
|
| 4 |
+
This repository contains the trained weights and architecture for a Hybrid Attention Transformer (HAT) fine-tuned for joint low-light enhancement and 4x super-resolution.
|
| 5 |
+
|
| 6 |
+
## Model Details
|
| 7 |
+
* **Architecture:** HAT (Hybrid Attention Transformer)
|
| 8 |
+
* **Task:** 4x Super-Resolution & Denoising on low-light images
|
| 9 |
+
* **Evaluation Metric:** PSNR
|
| 10 |
+
* **Performance:** Achieved ~39.57 PSNR on a blind Kaggle test set.
|
| 11 |
+
|
| 12 |
+
## Files Included
|
| 13 |
+
* `hat_phase2.pth`: The final fine-tuned PyTorch model weights.
|
| 14 |
+
* `hat_arch.py`: The architecture definition used to instantiate the model.
|
| 15 |
+
* `config.json`: The exact hyperparameters required to construct the architecture.
|