metadata
library_name: sklearn
tags:
- sklearn
- skops
- tabular-classification
model_format: skops
model_file: clf.skops
widget:
- structuredData:
x0:
- 25.861774444580078
- 13.925846099853516
- 18.626529693603516
x1:
- -9.131807327270508
- -9.77347183227539
- -9.504095077514648
x10:
- 1.9384498596191406
- 2.884918212890625
- 2.2260468006134033
x11:
- 3.0784831047058105
- 3.9418864250183105
- 4.06421422958374
x12:
- 2.991974353790283
- 2.9264330863952637
- 2.5255069732666016
x13:
- 2.345289707183838
- 2.3997442722320557
- 2.200080394744873
x14:
- 1.7882720232009888
- 1.840790867805481
- 1.383643388748169
x15:
- 1.6710506677627563
- 1.2678987979888916
- 0.47583726048469543
x16:
- 1.840790867805481
- 1.7882720232009888
- 1.0316907167434692
x17:
- 2.3997442722320557
- 2.345289707183838
- 1.8518061637878418
x18:
- 1.380855917930603
- 1.2926031351089478
- 1.0395294427871704
x19:
- 1.241168737411499
- 1.126420021057129
- 0.8134236931800842
x2:
- 4.62739896774292
- 5.171527862548828
- 4.921814441680908
x20:
- 0.9832149744033813
- 0.8152679800987244
- 0.38093870878219604
x21:
- 0.8598455786705017
- 0.6651478409767151
- 0.17098481953144073
x22:
- 0.9832149744033813
- 0.8152679800987244
- 0.38093870878219604
x23:
- 1.241168737411499
- 1.126420021057129
- 0.8134236931800842
x24:
- 2.725480556488037
- 3.022055149078369
- 3.3232314586639404
x25:
- 1.8365917205810547
- 2.0849626064300537
- 2.1735572814941406
x26:
- 1.22439444065094
- 1.251629114151001
- 1.4565647840499878
x3:
- 0.15449941158294678
- 0.03677806630730629
- 0.07167093455791473
x4:
- -0.024682553485035896
- -0.02837284840643406
- -0.029335789382457733
x5:
- -0.5647724866867065
- -0.19825565814971924
- -0.3138836622238159
x6:
- 4.030393123626709
- 5.093674182891846
- 5.913875102996826
x7:
- 3.9418864250183105
- 3.0784831047058105
- 3.5550312995910645
x8:
- 2.884918212890625
- 1.9384498596191406
- 1.8467140197753906
x9:
- 1.4331213235855103
- 1.9454820156097412
- 0.7261717319488525
Model description
LightGBM classifier of tree/non-tree pixels from aerial imagery trained on Zurich's Orthofoto Sommer 2014/15 using detectree.
Intended uses & limitations
Segment tree/non-tree pixels from aerial imagery
Training Procedure
[More Information Needed]
Hyperparameters
Click to expand
Hyperparameter | Value |
---|---|
boosting_type | gbdt |
class_weight | |
colsample_bytree | 1.0 |
importance_type | split |
learning_rate | 0.1 |
max_depth | -1 |
min_child_samples | 20 |
min_child_weight | 0.001 |
min_split_gain | 0.0 |
n_estimators | 200 |
n_jobs | |
num_leaves | 31 |
objective | |
random_state | |
reg_alpha | 0.0 |
reg_lambda | 0.0 |
subsample | 1.0 |
subsample_for_bin | 200000 |
subsample_freq | 0 |
Model Plot
LGBMClassifier(n_estimators=200)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LGBMClassifier(n_estimators=200)
Evaluation Results
Metrics calculated on a validation set of 1% of the test tiles
Metric | Value |
---|---|
accuracy | 0.87635 |
precision | 0.785237 |
recall | 0.756414 |
f1 | 0.770556 |
Dataset description
https://www.geolion.zh.ch/geodatensatz/2831
Preprocessing description
Images are resampled to 50 cm resolution. Train/test split based on image descriptors with 1% of tiles selected for training.
How to Get Started with the Model
[More Information Needed]
Model Card Authors
Martí Bosch
Model Card Contact
Citation
https://joss.theoj.org/papers/10.21105/joss.02172