Update README.md
Browse files
README.md
CHANGED
|
@@ -13,13 +13,13 @@ In correspondence with the code we released on [GitHub](https://github.com/), th
|
|
| 13 |
This folder contains the pretrained models, including:
|
| 14 |
|
| 15 |
- **ResNet18 Classification Backbone**: Pretrained on ImageNet (For more details, see the [PyTorch GitHub repository](https://github.com/pytorch/vision/tree/main/references/classification#resnet)) .
|
| 16 |
-
- **Binary Road Segmentation Model**: Initialized with the ImageNet classification backbone and trained using cascaded training with Swiss Map data.
|
| 17 |
|
| 18 |
## Binary_road_segmentation
|
| 19 |
-
This folder contains the final model weights used for extracting roads from the Siegfried Map.
|
| 20 |
|
| 21 |
## Road_classification_ensemble
|
| 22 |
-
This folder contains all the model weights for the final road classification ensemble.
|
| 23 |
|
| 24 |
## Citation
|
| 25 |
If you find our work useful or interesting, or if you use our code, please cite our paper as follows:
|
|
|
|
| 13 |
This folder contains the pretrained models, including:
|
| 14 |
|
| 15 |
- **ResNet18 Classification Backbone**: Pretrained on ImageNet (For more details, see the [PyTorch GitHub repository](https://github.com/pytorch/vision/tree/main/references/classification#resnet)) .
|
| 16 |
+
- **Binary Road Segmentation Model**: Initialized with the ImageNet classification backbone and trained using cascaded training with [Swiss Map](https://www.swisstopo.admin.ch/en/national-map-1-25000) data.
|
| 17 |
|
| 18 |
## Binary_road_segmentation
|
| 19 |
+
This folder contains the final model weights used for extracting roads from the [Siegfried Map](https://www.swisstopo.admin.ch/en/digital-siegfried-map-1-25000).
|
| 20 |
|
| 21 |
## Road_classification_ensemble
|
| 22 |
+
This folder contains all the model weights for the final road classification ensemble trained on the [Siegfried Map](https://www.swisstopo.admin.ch/en/digital-siegfried-map-1-25000).
|
| 23 |
|
| 24 |
## Citation
|
| 25 |
If you find our work useful or interesting, or if you use our code, please cite our paper as follows:
|