How sanjayimmanuel24/lulc-efficientnet-ensemble works
This repository is an experimental land-cover classification system for multispectral Sentinel-2/EuroSAT imagery. The main workflow builds reproducible folds, reads and transforms tiles, trains a dual-branch classifier, and produces fused predictions and evaluation results; separate scripts support single-tile prediction, calibration, robustness experiments, and interpretation. The graph retains the README’s documented selective-prediction and learned-gate capabilities. Some script-to-module links are based on the SOURCE INDEX import references; unsampled implementation details are not inferred.
Main entry points: run_cross_validation.py Cross-validation runner · ensemble.py Dual-branch model · predict.py Tile prediction · dataset.py Tile dataset
Components 24
Data preparation
- Stratified splits
lulc-project/src/data/splits.py - Tile dataset
lulc-project/src/data/dataset.py - Spectral indices
lulc-project/src/data/spectral_indices.py - Image transforms
lulc-project/src/data/transforms.py
Classification model
- Dual-branch model
lulc-project/src/models/ensemble.py - ECA attention
lulc-project/src/models/attention.py - Torch fusion
lulc-project/src/models/fusion_torch.py - Fusion reference
lulc-project/src/models/fusion.py - ResNet baseline
lulc-project/src/models/baseline.py - Smoothed loss
lulc-project/src/losses/label_smoothing_torch.py
Training and prediction
- Run configuration
lulc-project/src/config.py - Training loop
lulc-project/src/training/train.py - Cross-validation runner
lulc-project/scripts/run_cross_validation.py - Tile prediction
lulc-project/scripts/predict.py
Evaluation and reliability
- Temperature scaling
lulc-project/src/calibration/temperature_scaling.py - Classification metrics
lulc-project/src/evaluation/metrics.py - Statistical tests
lulc-project/src/evaluation/statistical_tests.py - Variant comparison
lulc-project/scripts/compare_variants.py - Selective prediction
lulc-project/scripts/selective_prediction.py - Learned fusion gate
lulc-project/scripts/train_fusion_gate.py - Grad-CAM
lulc-project/src/explainability/gradcam.py - Grad-CAM analysis
lulc-project/scripts/make_gradcam_figures.py
Other components
- Researcher
- EuroSAT-MS tiles
Connections 28
- Researcher → Cross-validation runner: runs folds
README.md - Researcher → Tile prediction: requests predictions
README.md - EuroSAT-MS tiles → Tile dataset: reads tiles
lulc-project/src/data/dataset.py - Tile dataset → Spectral indices: computes indices
lulc-project/src/data/dataset.py - Cross-validation runner → Run configuration: loads settings
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Stratified splits: builds folds
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Tile dataset: loads tiles
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Image transforms: transforms inputs
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Dual-branch model: trains model
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → ResNet baseline: selects baseline
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Training loop: runs training
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Temperature scaling: fits calibration
lulc-project/scripts/run_cross_validation.py - Cross-validation runner → Classification metrics: computes metrics
lulc-project/scripts/run_cross_validation.py - Training loop → Smoothed loss: builds criterion
lulc-project/src/training/train.py - Dual-branch model → ECA attention: uses attention
lulc-project/src/models/ensemble.py - Dual-branch model → Torch fusion: uses fusion
lulc-project/src/models/ensemble.py - Tile prediction → Tile dataset: loads tiles
lulc-project/scripts/predict.py - Tile prediction → Image transforms: transforms inputs
lulc-project/scripts/predict.py - Tile prediction → Dual-branch model: predicts classes
lulc-project/scripts/predict.py - Tile prediction → Fusion reference: reports fusion
lulc-project/scripts/predict.py - Variant comparison → Statistical tests: tests variants
lulc-project/scripts/compare_variants.py - Selective prediction → Statistical tests: tests risk
lulc-project/scripts/selective_prediction.py - Learned fusion gate → Stratified splits: loads folds
lulc-project/scripts/train_fusion_gate.py - Learned fusion gate → Tile dataset: loads tiles
lulc-project/scripts/train_fusion_gate.py - Learned fusion gate → Dual-branch model: caches logits
lulc-project/scripts/train_fusion_gate.py - Learned fusion gate → Fusion reference: compares fusion
lulc-project/scripts/train_fusion_gate.py - Grad-CAM analysis → Grad-CAM: generates maps
lulc-project/scripts/make_gradcam_figures.py - Grad-CAM analysis → Dual-branch model: explains model
lulc-project/scripts/make_gradcam_figures.py