Model card: detection overlay figure at the top (assets/overlay.png)
Browse files- .gitattributes +1 -0
- README.md +5 -0
- assets/overlay.png +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/overlay.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -13,6 +13,10 @@ tags:
|
|
| 13 |
|
| 14 |
# PV module detection models
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
Trained weights for the detection of individual photovoltaic (PV) modules in very high resolution satellite imagery: 10 segmentation networks, each with and without a Fine Optimization Module (FOM), 5 weights per configuration (one per data split). They are the models of
|
| 17 |
|
| 18 |
> N. Lukač, S. Seme, K. Sredenšek, G. Štumberger, D. Mongus, B. Žalik, M. Bizjak. **Detection and Optimization of Photovoltaic Arrays' Tilt Angles Using Remote Sensing Data.** *Applied Sciences* 15(7), 3598, 2025. https://doi.org/10.3390/app15073598
|
|
@@ -27,6 +31,7 @@ The code to run, evaluate and train them is [GeoSeg-PV](https://github.com/nikol
|
|
| 27 |
|---|---|
|
| 28 |
| `<config>/fold<k>.safetensors` | Weights of configuration `<config>` trained on split `k` (0 to 4). The metadata holds `arch`, `fom`, `fold`, `epoch`, `val_F1`, `test_F1` and `test_IoU` |
|
| 29 |
| `metrics.json` | Per configuration and split: epoch, validation F1, test F1 and IoU, test tiles, file size |
|
|
|
|
| 30 |
|
| 31 |
85 files, 11.2 GB. A configuration is named after its network and encoder, with `_fom` if it has the FOM.
|
| 32 |
|
|
|
|
| 13 |
|
| 14 |
# PV module detection models
|
| 15 |
|
| 16 |
+

|
| 17 |
+
|
| 18 |
+
*PV modules detected by `ftunetformer_fom/fold0.safetensors` (orange) on the 8 test tiles of split 0, with the F1 of each tile (made with `example/run_example.py --overlay` of GeoSeg-PV). Imagery © 2023 Google, Airbus, CNES/Airbus, Maxar Technologies; the imagery is not covered by the CC BY licence of the weights and is not otherwise redistributed.*
|
| 19 |
+
|
| 20 |
Trained weights for the detection of individual photovoltaic (PV) modules in very high resolution satellite imagery: 10 segmentation networks, each with and without a Fine Optimization Module (FOM), 5 weights per configuration (one per data split). They are the models of
|
| 21 |
|
| 22 |
> N. Lukač, S. Seme, K. Sredenšek, G. Štumberger, D. Mongus, B. Žalik, M. Bizjak. **Detection and Optimization of Photovoltaic Arrays' Tilt Angles Using Remote Sensing Data.** *Applied Sciences* 15(7), 3598, 2025. https://doi.org/10.3390/app15073598
|
|
|
|
| 31 |
|---|---|
|
| 32 |
| `<config>/fold<k>.safetensors` | Weights of configuration `<config>` trained on split `k` (0 to 4). The metadata holds `arch`, `fom`, `fold`, `epoch`, `val_F1`, `test_F1` and `test_IoU` |
|
| 33 |
| `metrics.json` | Per configuration and split: epoch, validation F1, test F1 and IoU, test tiles, file size |
|
| 34 |
+
| `assets/overlay.png` | The figure above (satellite imagery © Google and partners, not CC BY) |
|
| 35 |
|
| 36 |
85 files, 11.2 GB. A configuration is named after its network and encoder, with `_fom` if it has the FOM.
|
| 37 |
|
assets/overlay.png
ADDED
|
Git LFS Details
|