nikolukac commited on
Commit
cdaeb58
·
verified ·
1 Parent(s): 0a09dcf

Model card: detection overlay figure at the top (assets/overlay.png)

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. README.md +5 -0
  3. 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
+ ![PV modules detected by FT-UNetFormer + FOM (orange) on the 8 test tiles of split 0](assets/overlay.png)
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

  • SHA256: b3ebd4c21876567d8ce92aa4cfcf0bf950371be3eb872afd7ba3c8fc6b94038a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.18 MB