March 8, 2019

192 words 1 min read



GitHub repository for “Improving Video Generation for Multi-functional Applications”

repo name bernhard2202/improved-video-gan
repo link
language Python
size (curr.) 1169 kB
stars (curr.) 309
created 2017-09-13

Improving Video Generation for Multi-functional Applications

GitHub repository for “Improving Video Generation for Multi-functional Applications”

Paper Link

For more information please refer to our homepage.


  • Tensorflow 1.2.1
  • Python 2.7
  • ffmpeg

Data Format

Videos are stored as JPEGs of vertically stacked frames. Every frame needs to be at least 64x64 pixels; videos contain between 16 and 32 frames. For an example datasets see:



Important Parameters:

  • mode: one of ‘generate’, ‘predict’, ‘bw2rgb’, ‘inpaint’ depending on weather you want to generate videos, predict future frames, colorize videos or do inpainting.
  • batch_size: Recommended 64, for colorization use 32 for memory issues.
  • root_dir: root directory of dataset
  • index_file: must be in root_dir, containing a list of all training data clips; path relative to root_dir.
  • experiment_name: name of experiment
  • output_every: output loss to stdout and write to tensorboard summary every xx steps.
  • sample_every: generate a visual sample every xx steps.
  • save_model_very: save the model every xx steps.
  • recover_model: if true recover model and continue training
comments powered by Disqus