KaiyangZhou / pytorch-vsumm-reinforce

Unsupervised video summarization with deep reinforcement learning (AAAI'18)
MIT License
472 stars 150 forks source link

prepare dataset ? #70

Closed anbuharry closed 3 years ago

anbuharry commented 3 years ago

If you want to create a dataset for your own video you need Features is enough for training

there are 2 ways for getting a dataset one is to go and download the TVSum SumMe dataset page and download it others are the same

another method is for our own video you need to extract feature from the video and create a dataset through h5 create a dataset then rite inside the dataset