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

Captioning Result #12

Open LifeisFantasticLoL opened 5 years ago

LifeisFantasticLoL commented 5 years ago

Hi, Can I get your captioning result?

vijayvee commented 5 years ago

Hi, if you are interested in my trained weights, I just uploaded their checkpoints. You should be able to reproduce my results with these checkpoints.

MongTingWong commented 5 years ago

Hi, I am facing problem with FEATURE_VGG in data directory. it said there is not .npy file.

abhaygargab commented 4 years ago

You can extract the .npy files from Extract_Feats.py if you have installed caffe on your system. Else if you are facing problems installing caffe, you can follow zaoyehuo's code from https://github.com/keras-team/keras/issues/4301 to extract the features using keras pretrained VGG16 model.