README.md

Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward.

Implement with python=3.x https://github.com/KaiyangZhou/pytorch-vsumm-reinforce

Requirement

python=3.x

Pytorch

GPU

tabulate

Get started

git clone https://github.com/TorRient/Video-Summarization-Pytorch
cd Video-Summarization-Pytorch
mkdir dataset

1. Prepare dataset

Put your videos in folder dataset

python create_data.py --input dataset --output dataset/data.h5

2. Make splits

python create_split.py -d dataset/data.h5 --save-dir dataset --save-name splits  --num-splits 5

How to train

python train_video_summarisation.py -d dataset/data.h5

How to test

python video_summary.py --input path-to-video

Video summarization will be saved folder output/