Skip to content

purveshmakode24/captionr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

56 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

captionr

  • Smart AI bot to generate captions from images.

Directory tree structure

├── ...
├── media                  
│   ├── your model          # Required 
│   └── tokenizer.pkl       # Required
│               
├── ... 
└── README.md

Objective

  • To develop a framework which uses the abilities of neural networks to generate a caption for an image based on its features. Recurrent Neural Network (RNN) and CNN are used as a part of the encoder-decoder framework for the process of machine translation.
  • To use Convolutional Neural Network (CNN) in the encoder part, instead of RNN. Thus, image is transformed into required form of input data to feed into the decoder consisting of the RNN.
  • To transform the image into a multi-feature vector, characterizing its features. Flicker 8k dataset would be used for the same.
  • To generate captions using Greedy and Beam Search decoding.
  • Use text to speech API to convert generated caption to text.

Our Model and Tokenizer (links to download):

Model
tokenizer.pkl

Others - Link to Project Related Files

https://drive.google.com/drive/folders/16Mz7anvxs6J35farNKp4pnN4-X1JO8Lf

Contribution

If you're new to contributing to Open Source on Github, please check out this contribution guide for more details on how issues and pull requests work.

About

Smart AI bot to generate captions from images.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •