Views
No views yet
1
2git clone https://github.com/jgkwak95/AU-GAN.git
3cd AU-GAN
4
5# Create virtual environment
6conda create -y --name augan python=3.6.7
7conda activate augan
8
9conda install tensorflow-gpu==1.14.0 # Tensorflow 1.14
10pip install --no-cache-dir -r requirements.txt
111
2# Alderley (256x512)
3python main_uncer.py --dataset_dir alderley
4 --phase train
5 --experiment_name alderley_exp
6 --batch_size 8
7 --load_size 286
8 --fine_size 256
9 --use_uncertainty True
101
2# BDD100k (256x512)
3python main_uncer.py --dataset_dir bdd100k
4 --phase train
5 --experiment_name bdd_exp
6 --batch_size 8
7 --load_size 286
8 --fine_size 256
9 --use_uncertainty True
101
2# Alderley (256x512)
3python main_uncer.py --dataset_dir alderley
4 --phase test
5 --experiment_name alderley_exp
6 --batch_size 1
7 --load_size 286
8 --fine_size 256
9 1
2# BDD100k (256x512)
3python main_uncer.py --dataset_dir bdd100k
4 --phase test
5 --experiment_name bdd_exp
6 --batch_size 1
7 --load_size 286
8 --fine_size 256
9
10
@article{kwak2021adverse,
title={Adverse weather image translation with asymmetric and uncertainty-aware GAN},
author={Kwak, Jeong-gi and Jin, Youngsaeng and Li, Yuanming and Yoon, Dongsik and Kim, Donghyeon and Ko, Hanseok},
journal={arXiv preprint arXiv:2112.04283},
year={2021}
}