Giter VIP home page Giter VIP logo

scene-graph-for-videos's Introduction

Scene-Graph-For-Videos

Our KERN model is based on the KERN but we have modified the code for our custom image. Look into our blog post for detailed changes. Our Caption_Model is based on the text-summarization-tensorflow.

SetUp

  • Setup KERN following intructions here. It has to be accomodated to run on custom images(Mentioned in blog).

  • Download the dataset from charades & run the charaders_datamaker.py files to get the key frmaes from the videos.

  • This frames have to be placed inside the data directory of KERN.

  • Run Kern in sgdet mode by running the eval_kern_sgdet.sh file. ./scripts/eval_kern_sgdet.sh

  • You will get a pickle(.pkl) file containing scene graphs for all the image frames. Run the scene_graph_aggregator.py file to get a common scene graph for each video.

  • Run the Caption_Model for training by running

$ python train.py

For Testing

$ python test.py

scene-graph-for-videos's People

Contributors

dependabot[bot] avatar maurya-rohit avatar sitharakannan avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar

Forkers

eilsonh yogesh-iitj tongbaochen

scene-graph-for-videos's Issues

scene graph generation

Sir, i want to predict the scene graph for MSVD dataset. How can i change the scripts. Please suggest me any solution.

Question about charades_dataMaker.py

Hello,

When I ran the code of charades_dataMaker.py, the pickle files (e.g., kern_sgdet_1.pkl and kern_rel_recall_sgdet1.pkl) were generated. However, it showed all 'nan' after loading the pickle files, which means no object and relation was detected. Have you ever got this problem? Could you help tell me some potential solutions to solve this problem? Many thanks!

I cannot find your blog

hello，I am interested in your code,but I can not find your blog,so can you share your blog link? thanks

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.