项目作者: arijitray1993

项目描述 :
Music Video Generation using a Deep Generative Adversarial Network
高级语言: Python
项目地址: git://github.com/arijitray1993/music_video_gen.git
创建时间: 2020-04-24T20:39:38Z
项目社区:https://github.com/arijitray1993/music_video_gen

开源协议:GNU General Public License v3.0

下载


Music Video Generation using GAN’s

generated video sample

Requirements

  1. pip install librosa==0.7.2 torch==0.4.1 torchvision pillow scipy moviepy tqdm

Train on custom data

To train on your own music videos, you will need to create a folder of music videos and their corresponding mp3’s.
To do so, place music videos in a folder and do:

ffmpeg -i name_of_video.mp4 name_of_video.mp3 for each video mp4 file.
I will upload a script soon that automates this, but this has to be manual for now, sorry.

Then, simply run:

  1. cd Progressive-GAN-pytorch
  2. python train.py --path /path/to/folder/containing/video&music

Test on your music using pretrained checkpoint

To test on your own music file using a pretrained model, simply run:

  1. cd Progressive-GAN-pytorch
  2. python music2video.py --input_file /path/to/music.mp3 --outname /desired/output/videoname.mp4 --checkpoint optional/path/to/your_checkpoint_generator.pt
  3. # if you wish to use our checkpoint, do not use the --checkpoint argument

Citation

If you use this code, please consider citing:

@misc{raymusicvideogen, title={Swing Dance Video Generation using ProgressiveGAN}, author={Arijit Ray}, year={2020}, url={https://github.com/arijitray1993/music_video_gen/} }

Acknowledgements

The NVIDIA Progressive GAN code was modified from https://github.com/odegeasslbc/Progressive-GAN-pytorch