search

vijayvee / video-captioning

This repository contains the code for a video captioning system inspired by Sequence to Sequence -- Video to Text. This system takes as input a video and generates a caption in English describing the video.
MIT License
165 stars 66 forks source link

Can I get the extracted feature files of MSVD video as i am having trouble installing Caffe on my system. #19

Closed GauravKrRoy closed 4 years ago

AsimJalwana commented 5 years ago

Hey Gaurav, You can find them at https://github.com/vsubhashini/caffe/tree/recurrent/examples/s2vt. Where you can find the link to extracted features, currently it is https://www.dropbox.com/sh/whatkfg5mr4dr63/AACKCO3LwSsHK4_GOmHn4oyYa?dl=0.

abhaygargab commented 4 years ago

If this is still an issue, you can modify Extract_Feats.py following https://github.com/keras-team/keras/issues/4301, and extract the VGG features using keras pretrained VGG16 model. I used zaoyehuo's code given in the above link. In this you can get away with installing Caffe

vijayvee commented 4 years ago

Closing this issue as there are ways to download the extracted features at https://www.dropbox.com/sh/whatkfg5mr4dr63/AACKCO3LwSsHK4_GOmHn4oyYa?dl=0