GeoSeg is an open-source semantic segmentation toolbox based on PyTorch, pytorch lightning and timm, which mainly focuses on using advanced CNNs and Vision Transformers for remote sensing image segmentation.
-
Unified Benchmark
we provide a unified training script for various segmentation methods.
-
Simple and Effective
Thanks to pytorch lightning and timm , the code is easy for further development.
-
Support More Remote Sensing Datasets
- ISPRS Vaihingen and Potsdam
- UAVid
- LoveDA
- WHU building
- Inria Aerial Image Labelling
- More datasets will be supported in the future.
-
Multi-scale Training and Testing
-
Inference on Huge Remote Sensing Images
Prepare the following folders to organize this repo:
airs
├── GeoSeg (code)
├── pretrain_weights (save the pretrained weights like vit, swin, etc)
├── model_weights (save the model weights)
├── fig_results (save the masks predicted by models)
├── lightning_logs (CSV format training logs)
├── data
│ ├── LoveDA
│ │ ├── Train
│ │ │ ├── Urban
│ │ │ │ ├── images_png (original images)
│ │ │ │ ├── masks_png (original masks)
│ │ │ │ ├── masks_png_convert (converted masks used for training)
│ │ │ │ ├── masks_png_convert_rgb (original rgb format masks)
│ │ │ ├── Rural
│ │ │ │ ├── images_png
│ │ │ │ ├── masks_png
│ │ │ │ ├── masks_png_convert
│ │ │ │ ├── masks_png_convert_rgb
│ │ ├── Val (the same with Train)
│ │ ├── test
│ ├── uavid
│ │ ├── uavid_train (original)
│ │ ├── uavid_val (original)
│ │ ├── uavid_test (original)
│ │ ├── train (processed)
│ │ ├── val (processed)
│ ├── vaihingen
│ │ ├── train_images (original)
│ │ ├── train_masks (original)
│ │ ├── train_masks_eroded (original)
│ │ ├── val_images (original)
│ │ ├── val_masks (original)
│ │ ├── val_masks_eroded (original)
│ │ ├── test_images (original)
│ │ ├── test_masks (original)
│ │ ├── test_masks_eroded (original)
│ │ ├── train (processed)
│ │ ├── val (processed)
│ │ ├── test (processed)
│ ├── potsdam (the same with vaihingen)
Open the folder airs using Linux Terminal and create python environment:
conda create -n airs python=3.8
conda activate airs
conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge
pip install -r GeoSeg/requirements.txt
LoveDA
python GeoSeg/tools/loveda_mask_convert.py --mask-dir data/LoveDA/Train/Rural/masks_png --output-mask-dir data/LoveDA/Train/Rural/masks_png_convert
python GeoSeg/tools/loveda_mask_convert.py --mask-dir data/LoveDA/Train/Urban/masks_png --output-mask-dir data/LoveDA/Train/Urban/masks_png_convert
python GeoSeg/tools/loveda_mask_convert.py --mask-dir data/LoveDA/Val/Rural/masks_png --output-mask-dir data/LoveDA/Val/Rural/masks_png_convert
python GeoSeg/tools/loveda_mask_convert.py --mask-dir data/LoveDA/Val/Urban/masks_png --output-mask-dir data/LoveDA/Val/Urban/masks_png_convert
More datasets are updating.
LoveDA
python GeoSeg/train_supervision.py -c GeoSeg/config/loveda/dcswin.py
LoveDA
python GeoSeg/loveda_test.py -c GeoSeg/config/loveda/dcswin.py -o fig_results/loveda/dcswin_val --rgb --val -t 'd4'
LoveDA
python GeoSeg/loveda_test.py -c GeoSeg/config/loveda/dcswin.py -o fig_results/loveda/dcswin_test --rgb -t 'd4'
If you find this project useful in your research, please consider citing our papers.
We wish GeoSeg could serve the growing research of remote sensing by providing a unified benchmark and inspiring researchers to develop their own segmentation networks. Many thanks the following projects's contributions to GeoSeg.