Tabular Classification
Scikit-learn
Joblib
remote-sensing
tree-canopy
sentinel-2
philippines
metro-manila
civic-technology
Instructions to use xmpuspus/leaves-ph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use xmpuspus/leaves-ph with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("xmpuspus/leaves-ph", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Leaves.PH canopy classifier: canopy_clf_meta.json
Browse files- canopy_clf_meta.json +19 -0
canopy_clf_meta.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"features": [
|
| 3 |
+
"ndvi",
|
| 4 |
+
"dw",
|
| 5 |
+
"meta_h",
|
| 6 |
+
"esatree",
|
| 7 |
+
"red",
|
| 8 |
+
"nir",
|
| 9 |
+
"green",
|
| 10 |
+
"blue",
|
| 11 |
+
"gndvi",
|
| 12 |
+
"nir_red"
|
| 13 |
+
],
|
| 14 |
+
"threshold": 0.5,
|
| 15 |
+
"n_train": 656,
|
| 16 |
+
"n_canopy": 115,
|
| 17 |
+
"validation": "F1 0.78 / IoU 0.64 vs manual labels (region-grouped OOF CV, post-stratified); 4-feature model 0.75; NDVI>0.62 baseline 0.68 / 0.52",
|
| 18 |
+
"gold_labels": "data/canopy_model/master_labels.csv (n=656)"
|
| 19 |
+
}
|