cszn / SCUNet

Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)
https://link.springer.com/article/10.1007/s11633-023-1466-0
Apache License 2.0
619 stars 63 forks source link

Add requirements.txt #22

Open a-elrawy opened 9 months ago

ubergarm commented 4 months ago

Thanks @a-elrawy! Your requirements.txt sped me up in getting this repo running. Saved me the work!

Here is the quickstart for anyone playing with this repo:

# clone repo into your projects folder
cd ~/myprojects
git clone git@github.com:cszn/SCUNet.git

# install dependencies into local `.venv` folder
cd SCUNet
python3 -m venv ./venv
source ./venv/bin/activate
python3 -m pip install --upgrade pip
pip install -r requirements.txt # taken from this PR

# download models
python main_download_pretrained_models.py --models "SCUNet" --model_dir "model_zoo"

# try it out
python main_test_scunet_real_application.py --model_name scunet_color_real_psnr --testset_name real3

# see input images
sxiv -rt testsets/real3/*.png

# see output results
sxiv -rt results/real3_scunet_color_real_psnr/*.png