The improved version of AnimeGAN,Landscape photos/videos to anime

AnimeGANv2

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

Focus:

Anime style	Film	Picture Number	Quality	Download Style Dataset
Miyazaki Hayao	The Wind Rises	1752	1080p	Link
Makoto Shinkai	Your Name & Weathering with you	1445	BD
Kon Satoshi	Paprika	1284	BDRip

Different styles of training have different loss weights!

News:

The improvement directions of AnimeGANv2 mainly include the following 4 points:

[x] 1. Solve the problem of high-frequency artifacts in the generated image.
[x] 2. It is easy to train and directly achieve the effects in the paper.
[x] 3. Further reduce the number of parameters of the generator network. (generator size: 8.17 Mb), The lite version has a smaller generator model.
[x] 4. Use new high-quality style data, which come from BD movies as much as possible.

AnimeGAN can be accessed from here.

Requirements

python 3.6
tensorflow-gpu
- tensorflow-gpu 1.8.0 (ubuntu, GPU 1080Ti or Titan xp, cuda 9.0, cudnn 7.1.3)
- tensorflow-gpu 1.15.0 (ubuntu, GPU 2080Ti, cuda 10.0.130, cudnn 7.6.0)
opencv
tqdm
numpy
glob
argparse

Usage

1. Download vgg19

vgg19.npy

2. Download Train/Val Photo dataset

Link

3. Do edge_smooth

python edge_smooth.py --dataset Hayao --img_size 256

4. Calculate the three-channel(BGR) color difference

python data_mean.py --dataset Hayao

5. Train

python main.py --phase train --dataset Hayao --data_mean [13.1360,-8.6698,-4.4661] --epoch 101 --init_epoch 10
For light version: python main.py --phase train --dataset Hayao --data_mean [13.1360,-8.6698,-4.4661] --light --epoch 101 --init_epoch 10