Skip to content

Latest commit

 

History

History
124 lines (96 loc) · 4.31 KB

README.md

File metadata and controls

124 lines (96 loc) · 4.31 KB
Raw

AnimeGAN Pytorch

This is a Fork of ptran1203 Pytorch implementation of AnimeGAN for fast photo animation. This fork use more recents requirements.

Input Animation
c2 g2

Tested On

This fork of PyTorch-AnimeGAN successfully worked on :

  • OS : Windows 10/11
  • Python : 3.10.11

Quick start

git clone https://github.com/kitsumed/pytorch-animeGAN
cd pytorch-animeGAN

# Create a environment (Optional) 
py -3.10 -m venv venv
# Go into the environment
.\venv\Scripts\activate

# Install cpu or gpu requirments
pip install -r requirements_cpu.txt
pip install -r requirements_gpu.txt

Inference

On your local machine

Tip

--src and --out arguments can be a directory, a image file, or a video

Directory example:

python3 inference.py --weight /your/path/to/weight.pth --src /your/path/to/image_dir --out /path/to/output_dir

Video example:

Warning

Be careful when choosing --batch-size with video inferences, it might lead to CUDA memory error if the resolution of the video is too large

python3 inference.py --weight /your/path/to/weight.pth --src test_vid_3.mp4 --out test_vid_3_anime.mp4 --batch-size 4

From python code

from inference import Predictor

predictor= Predictor(
    '/your/path/to/weight.pth',
    # if set True, generated image will retain original color as input image
    retain_color=True
)

url = 'https://github.com/ptran1203/pytorch-animeGAN/blob/master/example/result/real/1%20(20).jpg?raw=true'

predictor.transform_file(url, "anime.jpg")

Note

In this example, a url is given to predictor.transform_file, you can also give a local file path.

Pretrained weight

Some weight where made available by ptran1203 here.

Training your own weight

1. Prepare dataset

1.1 To download dataset from the paper, run below command

wget -O anime-gan.zip https://github.com/ptran1203/pytorch-animeGAN/releases/download/v1.0/dataset_v1.zip
unzip anime-gan.zip

=> The dataset folder can be found in your current folder with named dataset

1.2 Create custom data from anime video

You need to have a video file located on your machine.

Step 1. Create anime images from the video

python3 script/video_to_images.py --video-path /path/to/your_video.mp4\
                                --save-path dataset/MyCustomData/style\
                                --image-size 256\

Step 2. Create edge-smooth version of dataset from Step 1.

python3 script/edge_smooth.py --dataset MyCustomData --image-size 256

2. Train animeGAN

To train the animeGAN from command line, you can run train.py as the following:

python3 train.py --anime_image_dir dataset/Hayao \
                --real_image_dir dataset/photo_train \
                --model v2 \                 # animeGAN version, can be v1 or v2
                --batch 8 \
                --amp \                      # Turn on Automatic Mixed Precision training
                --init_epochs 10 \
                --exp_dir runs \
                --save-interval 1 \
                --gan-loss lsgan \           # one of [lsgan, hinge, bce]
                --init-lr 1e-4 \
                --lr-g 2e-5 \
                --lr-d 4e-5 \
                --wadvd 300.0\               # Aversarial loss weight for D
                --wadvg 300.0\               # Aversarial loss weight for G
                --wcon 1.5\                  # Content loss weight
                --wgra 3.0\                  # Gram loss weight
                --wcol 30.0\                 # Color loss weight
                --use_sn\                    # If set, use spectral normalization, default is False