Ubuntu 18.04.5 LTS 버전에서 이미지 변환 모델 AnimeGANv2와 CartoonGan을 구동하기 위해 개발 환경을 구축해 보자
https://repo.anaconda.com/archive/.winzip/
// 예시
$ wget https://repo.anaconda.com/archive/Anaconda3-2019.10-Linux-x86_64.sh
// 예시
$ bash Anaconda3-2019.10-Linux-x86_64.sh
$ source ~/.bashrc
(base) $ conda update conda
(base) $ conda update anaconda
https://github.com/TachibanaYoshino/AnimeGANv2
(base) $ conda create -n anigan python=3.6
(base) $ conda activate anigan
(anigan) $ python -m pip install --upgrade pip
(anigan) $ git clone https://github.com/TachibanaYoshino/AnimeGANv2.git
(anigan) $ cd ./AnimeGANv2
(anigan) $ pip install tensorflow-gpu==1.15
(anigan) $ pip install argparse
(anigan) $ conda install opencv
(anigan) $ conda install tqdm
(anigan) $ conda install glob2
$ python test.py --checkpoint_dir checkpoint/generator_Hayao_weight --test_dir dataset/test/HR_photo --save_dir Hayao/HR_photo
https://github.com/JSeokjun/CartoonGan-tensorflow
(base) $ conda create -n cartgan python=3.6
(base) $ conda activate cartgan
(cartgan) $ python -m pip install --upgrade pip
(cartgan) $ git clone https://github.com/mnicnc404/CartoonGan-tensorflow.git
(cartgan) $ cd ./CartoonGan-tensorflow
(cartgan) $ pip install tensorflow==2.0
(cartgan) $ conda install tqdm
(cartgan) $ pip install imageio
(cartgan) $ pip install tb-nightly
$ python cartoonize.py --input_dir input_images --output_dir output_images --styles shinkai hayao --comparison_view horizontal
담비와시작하는머신러닝. (2020, February 3). [ Anaconda ] 아나콘다 설치 방법 및 기초 사용법 ( Linux ). Retrieved 23:49, September 4, 2023, from https://dambi-ml.tistory.com/6
목포대학교 컴퓨터공학과 손현승 교수. (2022, November 3). Deep Leaning + Animation. Retrieved 23:51, September 4, 2023, from https://dream.mokpo.ac.kr/bbs/ce/614/192100/download.do