face-vid2vid

Usage

cd datasets
wget https://yt-dl.org/downloads/latest/youtube-dl -O youtube-dl
chmod a+rx youtube-dl
python load_videos.py --workers=8
cd ..

Put hopenet_robust_alpha1.pkl under the repo root

python train.py --batch_size=4 --gpu_ids=0,1,2,3 --num_epochs=100 (--ckp=10)

On 2080Ti, setting batch_size=4 makes up gpu memory

Reconstruction：

python evaluate.py --ckp=99 --source=r --driving=datasets/vox/test/id10280#NXjT3732Ekg#001093#001192.mp4

The first frame is used as source by default

Motion transfer：

python evaluate.py --ckp=99 --source=test.png --driving=datasets/vox/test/id10280#NXjT3732Ekg#001093#001192.mp4

Example after training for 7 days on 4 2080Ti:

Face Frontalization：

python evaluate.py --ckp=99 --source=f --driving=datasets/vox/train/id10192#S5yV10aCP7A#003200#003334.mp4

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
datasets		datasets
README.md		README.md
augmentation.py		augmentation.py
dataset.py		dataset.py
distributed.py		distributed.py
evaluate.py		evaluate.py
logger.py		logger.py
losses.py		losses.py
models.py		models.py
modules.py		modules.py
output-8.gif		output-8.gif
train.py		train.py
trainer.py		trainer.py
utils.py		utils.py