Improved Video GAN 视频生成框架

Improved Video GAN 视频生成框架

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.

Requirements

Tensorflow 1.2.1Python 2.7ffmpeg

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: http://carlvondrick.com/tinyvideo/#data

Training

python main_train.py

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 datasetindex_file: must be in root_dir, containing a list of all training data clips; path relative to root_dir.experiment_name: name of experimentoutput_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

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。