Image Segmentation
TerraTorch
English
Pytorch
mmsegmentation
segmentation
Flood mapping
Sentinel-2
Geospatial
Foundation model
Instructions to use ibm-nasa-geospatial/Prithvi-EO-1.0-100M-sen1floods11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TerraTorch
How to use ibm-nasa-geospatial/Prithvi-EO-1.0-100M-sen1floods11 with TerraTorch:
from terratorch.registry import BACKBONE_REGISTRY model = BACKBONE_REGISTRY.build("ibm-nasa-geospatial/Prithvi-EO-1.0-100M-sen1floods11") - Notebooks
- Google Colab
- Kaggle
Commit ·
3473037
1
Parent(s): dac3258
Update README.md
Browse filesadd feedback link
README.md
CHANGED
|
@@ -70,4 +70,8 @@ Finetuning took ~1 hour on an NVIDIA V100.
|
|
| 70 |
|
| 71 |
|
| 72 |
### Inference
|
| 73 |
-
The github repo includes an inference script that allows running the flood mapping model for inference on Sentinel-2 images. These inputs have to be geotiff format, including 6 bands for a single time-step described above (Blue, Green, Red, Narrow NIR, SWIR, SWIR 2) in order. There is also a **demo** that leverages the same code **[here](https://huggingface.co/spaces/ibm-nasa-geospatial/Prithvi-100M-sen1floods11-demo)**.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
### Inference
|
| 73 |
+
The github repo includes an inference script that allows running the flood mapping model for inference on Sentinel-2 images. These inputs have to be geotiff format, including 6 bands for a single time-step described above (Blue, Green, Red, Narrow NIR, SWIR, SWIR 2) in order. There is also a **demo** that leverages the same code **[here](https://huggingface.co/spaces/ibm-nasa-geospatial/Prithvi-100M-sen1floods11-demo)**.
|
| 74 |
+
|
| 75 |
+
### Feedback
|
| 76 |
+
|
| 77 |
+
Your feedback is invaluable to us. If you have any feedback about the model, please feel free to share it with us. You can do this by submitting issues on our open-source repository, [hls-foundation-os](https://github.com/NASA-IMPACT/hls-foundation-os/issues), on GitHub.
|