Instructions to use FPSica/beyond-backscatter-grd-gee with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use FPSica/beyond-backscatter-grd-gee with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://FPSica/beyond-backscatter-grd-gee") - Notebooks
- Google Colab
- Kaggle
Upload model_metadata.json with huggingface_hub
Browse files- model_metadata.json +12 -0
model_metadata.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "Beyond Backscatter GRD/GEE coherence estimator",
|
| 3 |
+
"framework": "tensorflow_keras",
|
| 4 |
+
"weights_filename": "model.weights.h5",
|
| 5 |
+
"config_filename": "config.yaml",
|
| 6 |
+
"source_weight_set": "GEE",
|
| 7 |
+
"input_convention": "two Sentinel-1 GRD linear sigma0 images from Google Earth Engine, channel order [t1, t2]",
|
| 8 |
+
"model_preprocessing": "linear sigma0 -> dB -> clip [-20, 0] -> normalize [0, 1]",
|
| 9 |
+
"output_convention": "predicted coherence in [0, 1], first model output channel",
|
| 10 |
+
"github_repo": "https://github.com/FPSica/BeyondBackscatter",
|
| 11 |
+
"colab_notebook": "https://colab.research.google.com/github/FPSica/BeyondBackscatter/blob/main/notebooks/back2coh_grd_gee_colab.ipynb"
|
| 12 |
+
}
|