Skip to content

Instantly share code, notes, and snippets.

@kuniiskywalker
Last active April 25, 2021 12:56
Show Gist options
  • Save kuniiskywalker/e3b6132782e933dccf2738d346d5eaf6 to your computer and use it in GitHub Desktop.
Save kuniiskywalker/e3b6132782e933dccf2738d346d5eaf6 to your computer and use it in GitHub Desktop.

environment

os: windows 10
gpu: NVIDIA GeForce GTX 1060 6GB

cuda setup

cuda toolkit

https://developer.nvidia.com/cuda-10.0-download-archive?target_os=Windows&target_arch=x86_64&target_version=10&target_type=exenetwork

CUDA Toolkit 10.0 Archive

cuDNN

https://developer.nvidia.com/rdp/cudnn-archive

Download cuDNN v7.6.2 (July 22, 2019), for CUDA 10.0

Windows setup

https://www.tensorflow.org/install/gpu#windows_setup

application setup

$ conda create -n animegan python=3.6
$ conda activate animegan
$ pip install tensorflow-gpu==1.15.0
$ pip install tqdm
$ pip install scipy
$ pip install opencv-python
$ git clone https://github.com/TachibanaYoshino/AnimeGANv2
$ cd AnimeGAN-master

photo convert

python test.py --checkpoint_dir checkpoint/generator_Hayao_weight --test_dir dataset/test/HR_photo --style_name Paprika/HR_photo

movie convert

python video2anime.py --video video/input/お花見.mp4 --checkpoint_dir checkpoint/generator_Paprika_weight
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment