🌟🌟🌟 Here is the official project of 🎻CoDA. We only release the checkpoint for inference now and will release the code of Chain-of-Domain and Severity-Aware Visual Prompt Tuning later.
🔥🔥🔥CoDA is a UDA methodology that boosts models to understand all adverse scenes (☁️,☔,❄️,🌙) by highlighting the discrepancies within these scenes. CoDA achieves state-of-the-art performances on widely used benchmarks.
Experiments | mIoU | Checkpoint | Configs |
---|---|---|---|
Cityscapes |
72.6 | - | - |
Cityscapes |
60.9 | - | - |
Cityscapes |
61.0 | - | - |
Cityscapes |
61.2 | - | - |
Cityscapes |
59.2 | - | - |
Cityscapes |
41.6 | - | - |
cd CoDA
python ./tools/download_ck.py
or you can manually download checkpoints from Google Drive.
Before run demo, first configure the PYTHONPATH, or you will encounter error like 'can not found tools...'.
cd CoDA
export PYTHONPATH=.:$PYTHONPATH
or directly modify the .bashrc file
vi ~/.bashrc
export PYTHONPATH=your path/CoDA:$PYTHONPATH
source ~/.bashrc
python ./tools/image_demo.py --img ./images/night_demo.png --config ./configs/coda/csHR2acdcHR_coda.py --checkpoint ./pretrained/CoDA_cs2acdc.pth
python ./tools/image_demo.py --img_dir ./acdc_dir --config ./configs/coda/csHR2acdcHR_coda.py --checkpoint ./pretrained/CoDA_cs2acdc.pth --out_dir ./workdir/cs2acdc
python ./tools/train.py --config ./configs/coda/csHR2acdcHR_coda.py --work-dir ./workdir/cs2acdc