Baseline models for the BDAPPV dataset — aerial images of rooftop photovoltaic installations in France and Belgium.
Source du modèle
Description de la source
Baseline models for the BDAPPV dataset — aerial images of rooftop photovoltaic installations in France and Belgium.
Paper: Kasmi et al., Scientific Data, 2023 — arXiv:2209.03726
Sources
1 sourceVérifié 17 sept.
Artefacts du modèle
4 artefactsExtraits de sources
2 extraitsTwo architectures, trained independently on each imagery provider:
| File | Task | Architecture | Provider |
|---|---|---|---|
deeplab_google_best.pth | Segmentation | DeepLabV3-ResNet101 | |
deeplab_ign_best.pth | Segmentation | DeepLabV3-ResNet101 | IGN |
inception_google_best.pth | Classification | InceptionV3 | |
inception_ign_best.pth | Classification | InceptionV3 | IGN |
Note on training data and licensing. Checkpoints fine-tuned on the
Google subset of BDAPPV (*_google_*) derive from imagery distributed
under CC-BY-NC 4.0; commercial users should prefer the IGN-trained
checkpoints (*_ign_*, CC-BY 4.0 imagery) or assess accordingly. All
models are initialized from Mayer et al. (2022) checkpoints — see their
repository for base model licensing.
Three evaluation tracks are defined:
Track 1 — Segmentation (single provider) Train and evaluate on the same provider. Report IoU and F1 on the test split.
Track 2 — Classification (single provider) Train and evaluate on the same provider. Report accuracy and F1 on the test split.
Track 3 — Distribution shift (cross-provider) Train on Google, evaluate on IGN test split. This is the primary robustness benchmark. Report IoU.
Rules:
Models evaluated on the official test split (spatial holdout by French department — see dataset card for details).
| Train | Test | IoU | F1 | n (test) |
|---|---|---|---|---|
| 0.884 | 0.937 | 1,935 | ||
| IGN | IGN | 0.735 | 0.844 | 1,239 |
| IGN | 0.561 | 0.709 | 1,239 | |
| IGN | 0.657 | 0.786 | 1,935 |
| Train | Test | Accuracy | Precision | Recall | F1 | n (test) |
|---|---|---|---|---|---|---|
| 0.952 | 0.990 | 0.912 | 0.949 | 3,884 | ||
| IGN | IGN | 0.640 | 0.831 | 0.309 | 0.451 | 2,593 |
| IGN | 0.592 | 0.815 | 0.188 | 0.306 | 2,593 | |
| IGN | 0.543 | 1.000 | 0.083 | 0.153 | 3,884 |
Note on classification cross-provider results: the IGN-trained model collapses on Google imagery (Recall=0.08, Precision=1.0), indicating the model rarely predicts positives — a degenerate operating point. This illustrates the severity of the distribution shift documented in Kasmi et al. (2025).
A model.py helper is included in this repo to simplify loading:
from huggingface_hub import hf_hub_download
import importlib.util
path = hf_hub_download("gabrielkasmi/bdappv-models", "model.py")
spec = importlib.util.spec_from_file_location("bdappv_model", path)
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
seg = mod.load_segmentation_model("google") # or "ign"
clf = mod.load_classification_model("google") # or "ign"
Both functions return the model in eval() mode. An optional device argument is supported ("cpu", "cuda", "mps").
Models trained on the official BDAPPV splits using:
Training scripts available in the BDAPPV dataset repository.
If you use these models, please cite:
@article{kasmi2022towards,
title={Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping},
author={Kasmi, Gabriel and Dubus, Laurent and Blanc, Philippe and Saint-Drenan, Yves-Marie},
journal={arXiv preprint arXiv:2207.07466},
year={2022}
}
inception_google_best.pth
pth · 93,2 MB · SHA-256 ba031e7d0eac…b008 · Hugging Face
--- license: cc-by-4.0 tags: - image-segmentation - image-classification - solar-panels - photovoltaic - remote-sensing - aerial-imagery - pytorch datasets: - gabrielkasmi/bdappv --- # BDAPPV Models Baseline models for the [BDAPPV dataset](https://huggingface.co/datasets/gabrielkasmi/bdappv) — aerial images of rooftop photovoltaic installations in France and Belgium. **Paper:** [Kasmi et al., Scientific Data, 2023](https://doi.org/10.1038/s41597-023-01951-4) — [arXiv:2209.03726](https://arxiv.org/abs/2209.03726) --- ## Models Two architectures, trained independently on each imagery provider: | File | Task | Architecture | Provider | |------|------|-------------|----------| | `deeplab_google_best.pth` | Segmentation | DeepLabV3-ResNet101 | Google | | `deeplab_ign_best.pth` | Segmentation | DeepLabV3-ResNet101 | IGN | | `inception_google_best.pth` | Classification | InceptionV3 | Google | | `inception_ign_best.pth` | Classification | InceptionV3 | IGN | **Note on training data and licensing.** Checkpoints fine-tuned on the Google subset of BDAPPV (`*_google_*`) derive from imagery distributed under CC-BY-NC 4.0; commercial users should prefer the IGN-trained checkpoints (`*_ign_*`, CC-BY 4.0 imagery) or assess accordingly. All models are initialized from Mayer et al. (2022) checkpoints — see their repository for base model licensing. --- ## Benchmark protocol Three evaluation tracks are defined: **Track 1 — Segmentation (single provider)** Train and evaluate on the same provider. Report IoU and F1 on the test split. **Track 2 — Classification (single provider)** Train and evaluate on the same provider. Report accuracy and F1 on the test split. **Track 3 — Distribution shift (cross-provider)** Train on Google, evaluate on IGN test split. This is the primary robustness benchmark. Report IoU. Rules: - The test split must not be used for model selection or hyperparameter tuning — validation split only. - The spatial holdout by department must not be modified. Re-splitting invalidates comparability with published results. - For Track 3, only the Google training split may be used for training. --- ## Results Models evaluated on the official test split (spatial holdout by French department — see dataset card for details). ### Segmentation (DeepLabV3-ResNet101) | Train | Test | IoU | F1 | n (test) | |-------|------|-----|----|----------|...
Source context: 0 downloads · 2 likes · Pipeline image-classification · Repo gabrielkasmi/bdappv-models