README.md

metadata

title: Cloudseg
emoji: 📚
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 4.40.0
app_file: app.py
pinned: false
license: apache-2.0

Cloud Segmentation

Datasets

cloudseg
├── src
├── configs
├── data
│   ├── hrcwhu
│   │   ├── train.txt
│   │   ├── test.txt
│   │   ├── img_dir
│   │   │   ├── train
│   │   │   ├── test
│   │   ├── ann_dir
│   │   │   ├── train
│   │   │   ├── test

Supported Methods

• UNet (MICCAI 2016)
• CDNetv1 (TGRS 2019)
• CDNetv2 (TGRS 2021)
• DBNet (TGRS 2022)
• HrCloudNet (JEI 2024)
• McdNet (International Journal of Applied Earth Observation and Geoinformation 2024)
• Scnn (ISPRS 2024)

Installation

git clone https://github.com/XavierJiezou/cloudseg.git
cd cloudseg
conda env create -f environment.yaml
conda activate cloudseg

Usage

Train model with default configuration

# train on CPU
python src/train.py trainer=cpu

# train on GPU
python src/train.py trainer=gpu

Train model with chosen experiment configuration from configs/experiment/

python src/train.py experiment=experiment_name.yaml

Tranin Example

python src/train.py experiment=hrcwhu_cdnetv1.yaml

You can override any parameter from command line like this

python src/train.py trainer.max_epochs=20 data.batch_size=64

Visualization in wandb

python wand_vis.py --model-name model_name

Example

python wand_vis.py --model-name cdnetv1