aerovilab-ahu/lwganet

How aerovilab-ahu/lwganet works

LWGANet is a PyTorch remote-sensing vision repository spanning image classification, oriented object detection, semantic segmentation, and change detection. Users prepare task-specific imagery and labels, configure a model, then train or run inference to obtain class, object, mask, or change predictions. The shared architectural idea is the lightweight LWGANet backbone, while each task has its own data and model stack. The graph preserves documented task capabilities; some subsystem internals are unsampled, so only evidenced or README-documented connections are shown.

Main entry points: cfg.py Task configuration · train.py A2Net training · main.py CLAFA training entry · train_supervision.py Segmentation training

Components 33

Shared Backbone

LWGANet models classification/models

Classification

Classifier training classification/train.py
Classification data utilities classification/utils.py
Alternative backbones classification/models
EdgeNeXt blocks classification/models/edgenext
Dataset splitting classification/split_datasets/split_train_val_dataset.py

Oriented Detection

Detection training entry detection/tools/train.py
Train and inference APIs detection/mmrotate/apis
Rotated datasets detection/mmrotate/datasets
Detector architectures detection/mmrotate/models/detectors
LWGANet detector backbone detection/mmrotate/models/backbones/lwganet.py
Detection heads detection/mmrotate/models/dense_heads
Rotated-box utilities detection/mmrotate/core
Patch inference detection/mmrotate/apis/inference.py

Semantic Segmentation

Segmentation training segmentation/train_supervision.py
Task configuration segmentation/tools/cfg.py
Segmentation datasets segmentation/geoseg/datasets
Dataset transforms segmentation/geoseg/datasets/transform.py
Segmentation models segmentation/geoseg/models
UNetFormer model segmentation/geoseg/models/UNetFormer.py
Segmentation losses segmentation/geoseg/losses
Large-image inference segmentation/inference_huge_image.py
UAVid inference segmentation/inference_uavid.py

Change Detection

A2Net training change_detection/A2Net_LWGANet/train.py
A2Net dataset change_detection/A2Net_LWGANet/dataset.py
A2Net transforms change_detection/A2Net_LWGANet/Transforms.py
A2Net model family change_detection/A2Net_LWGANet/models
CLAFA training entry change_detection/CLAFA_LWGANet/main.py
CLAFA dataset change_detection/CLAFA_LWGANet/data/cd_dataset.py
CLAFA model factory change_detection/CLAFA_LWGANet/model/create_model.py
CLAFA LWGANet backbone change_detection/CLAFA_LWGANet/model/backbone/lwganet.py
Change metrics change_detection/CLAFA_LWGANet/util/metric_tool.py

Other components

Researcher

Connections 29

Researcher → Classifier training: trains classifier README.md
Researcher → Detection training entry: trains detector README.md
Researcher → Segmentation training: trains segmenter README.md
Researcher → A2Net training: trains change model README.md
Researcher → CLAFA training entry: trains change model README.md
Classifier training → Classification data utilities: uses utilities classification/train.py
Classification data utilities → LWGANet models: selects backbone classification/utils.py
Classification data utilities → Alternative backbones: selects models classification/utils.py
EdgeNeXt blocks → Alternative backbones: implements backbone classification/models/edgenext/edgenext.py
Detection training entry → Train and inference APIs: uses APIs detection/tools/train.py
Train and inference APIs → Rotated-box utilities: imports utilities detection/mmrotate/apis/inference.py
Patch inference → Rotated-box utilities: merges patches detection/mmrotate/apis/inference.py
LWGANet detector backbone → LWGANet models: implements backbone
Segmentation training → Task configuration: loads configuration segmentation/train_supervision.py
Task configuration → Segmentation datasets: configures datasets
Task configuration → UNetFormer model: configures model
Task configuration → Segmentation losses: configures losses
Segmentation datasets → Dataset transforms: uses transforms segmentation/geoseg/datasets/uavid_dataset.py
Large-image inference → Task configuration: loads configuration segmentation/inference_huge_image.py
Large-image inference → Segmentation training: loads trained model segmentation/inference_huge_image.py
UAVid inference → Task configuration: loads configuration segmentation/inference_uavid.py
UAVid inference → Segmentation training: loads trained model segmentation/inference_uavid.py
A2Net training → A2Net dataset: loads data change_detection/A2Net_LWGANet/train.py
A2Net training → A2Net transforms: applies transforms change_detection/A2Net_LWGANet/train.py
A2Net training → A2Net model family: uses model change_detection/A2Net_LWGANet/train.py
CLAFA training entry → CLAFA dataset: loads data change_detection/CLAFA_LWGANet/main.py
CLAFA training entry → CLAFA model factory: creates model change_detection/CLAFA_LWGANet/main.py
CLAFA training entry → Change metrics: reports metrics change_detection/CLAFA_LWGANet/main.py
CLAFA model factory → CLAFA LWGANet backbone: builds network change_detection/CLAFA_LWGANet/model/create_model.py

More Jupyter Notebook diagrams: zamanzadeh/carla · maximilianigl/dvrl · illiaovcharenko/lung-segmentation · radar-lab/mmfall · satcom-telma/ma-drl_routing_simulator

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·