Skip to content

Deployment repo for the trained stylised-controllable-image-captioning model.

License

Notifications You must be signed in to change notification settings

riven314/TweakStory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

95 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

logo

instagram license python

Tweak Story is an open-source project towards generating controllable Instagram captions, powered by PyTorch, Transformers and Streamlit. We apply attention-based condition LSTM network to generate engaging captions that can be tweaked by our users. With different attributes we offer, user can easily mix and match different combination of attributes for their own flavor. In current stage, we offer sentence length and emoji flag as available attributes.

Demo

You can find an online version of Tweak Story here.

demo

App Structure

app has 4 major parts :

  1. app.py - Main script for launching our Streamlit app
  2. src - This folder contains all utility scripts for powering the app
  3. ckpts - This folder contains model checkpoint, word map and configuration file for our model
  4. demo - This folder contains example images you can try out in our app

Prerequisites (optional)

Download the following files and place them into ckpts folder

Install and Run in Docker

Clone the repo and navigate to the repo:

git clone https://github.com/riven314/TweakStory.git
cd TweakStory/app

Build and run the docker image locally:

make run

Navigate to http://localhost:8501 for the app. (Streamlit runs on port 8501 by default)

Shutdown the server:

make stop 

Note : When you'll run the container for the first time it will download a resnet101 model. The Streamlit app is run in CPU.

Run Unit Test

cd TweakStory/app
pytest -s tests

Model Structure

TODO

About This Project

This project is a part of Data Science Incubator (Summer 2020) organized by Made With ML, jointly developed by Alex Lau and Naman Bhardwaj. We constantly look for better generation quality and deployment strategy. We welcome your contributions and please contact us if you do!

Acknowledgements

Our work is mainly based upon the following published research:

@article{Xu2015show,
    title={Show, Attend and Tell: Neural Image Caption Generation with Visual Attention},
    author={Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron and Salakhutdinov, Ruslan and Zemel, Richard and Bengio, Yoshua},
    journal={arXiv preprint arXiv:1502.03044},
    year={2015}
} 
@article{Ficler2017show,
    title={Controlling Linguistic Style Aspects in Neural Language Generation},
    author={Jessica Ficler and Yoav Goldberg},
    journal={arXiv preprint arXiv:1707.02633},
    year={2017}
} 

About

Deployment repo for the trained stylised-controllable-image-captioning model.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published