Sync WindFormer model weights and configuration
Browse files
README.md
CHANGED
|
@@ -1,4 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# WindFormer
|
|
|
|
| 2 |
*Developed for the ESAWAAI Project and ESAWAAI Legacy Dataset HF Bucket*
|
| 3 |
|
| 4 |
A PyTorch implementation that loads a pre-trained `WindFormerDist` architecture and prepares it in evaluation mode for inference.
|
|
@@ -15,7 +24,7 @@ pip install torch safetensors
|
|
| 15 |
|
| 16 |
## File Structure
|
| 17 |
|
| 18 |
-
| File | Description |
|
| 19 |
| :--- | :--- |
|
| 20 |
| `main.py` | Script to load the model weights and set it to evaluation mode |
|
| 21 |
| `windformer.py` | Model architecture definition for `WindFormerDist` |
|
|
@@ -26,11 +35,19 @@ pip install torch safetensors
|
|
| 26 |
To run the model inference pipeline:
|
| 27 |
|
| 28 |
```bash
|
| 29 |
-
python
|
| 30 |
```
|
| 31 |
|
| 32 |
## Model Weights & Configuration
|
| 33 |
|
| 34 |
Weights are stored using [Safetensors](https://github.com/huggingface/safetensors).
|
| 35 |
|
| 36 |
-
> **Important:** The instantiation parameters (e.g., `WindFormerDist(fusion=False)`) must strictly match the configuration used during training. Any discrepancy will cause `load_state_dict` to fail due to missing or unexpected keys.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- pytorch
|
| 4 |
+
- safetensors
|
| 5 |
+
- windformer
|
| 6 |
+
- esawaii
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
# WindFormer
|
| 10 |
+
|
| 11 |
*Developed for the ESAWAAI Project and ESAWAAI Legacy Dataset HF Bucket*
|
| 12 |
|
| 13 |
A PyTorch implementation that loads a pre-trained `WindFormerDist` architecture and prepares it in evaluation mode for inference.
|
|
|
|
| 24 |
|
| 25 |
## File Structure
|
| 26 |
|
| 27 |
+
| **File** | **Description** |
|
| 28 |
| :--- | :--- |
|
| 29 |
| `main.py` | Script to load the model weights and set it to evaluation mode |
|
| 30 |
| `windformer.py` | Model architecture definition for `WindFormerDist` |
|
|
|
|
| 35 |
To run the model inference pipeline:
|
| 36 |
|
| 37 |
```bash
|
| 38 |
+
python main.py
|
| 39 |
```
|
| 40 |
|
| 41 |
## Model Weights & Configuration
|
| 42 |
|
| 43 |
Weights are stored using [Safetensors](https://github.com/huggingface/safetensors).
|
| 44 |
|
| 45 |
+
> **Important:** The instantiation parameters (e.g., `WindFormerDist(fusion=False)`) must strictly match the configuration used during training. Any discrepancy will cause `load_state_dict` to fail due to missing or unexpected keys.
|
| 46 |
+
|
| 47 |
+
## Cite
|
| 48 |
+
|
| 49 |
+
Benchaabane, A., Toft, L. D. D. S., Ristea, N.-C., Dimitriadou, K., Husson, R., Hasager, C. B., Anghel, A., Longépé, N., Mouche, A., Grouazel, A., & Datcu, M. (2026). Explainable SAR measurements for Wind Assessment with Artificial Intelligence (ESAWAAI).
|
| 50 |
+
|
| 51 |
+
## License
|
| 52 |
+
|
| 53 |
+
This dataset and its associated documentation are released under the terms of the [Creative Commons Attribution 4.0 International (CC-BY 4.0)](https://creativecommons.org/licenses/by/4.0/) license.
|