Giter Site home page Giter Site logo

sainathomdas / image-captioning Goto Github PK

View Code? Open in Web Editor NEW

This project forked from faizan-e-mustafa/image-captioning

0.0 1.0 0.0 55.4 MB

It takes in picture and describe what going on in the picture in plain English.

Jupyter Notebook 100.00%

image-captioning's Introduction

Keras implementation of Image-Captioning

Image captioning is a task that involves computer vision as well as Natural language processing. It takes an image and is able to describe whats going on in the image in plain English.

  • Keras With Tensorflow back-end
  • InceptionV3 for encoding
  • LSTM for decoding
  • Greedy as well as Beam serch was used.
  • Hyper parameters used
Hyper parameter Value
Embedding size 300
Vocabulary size 8256
Dropout 0.5
Batch Size 128
LSTM 1 Output 256
LSTM 1 Output 1000

I have also written a blog post describing my experience of implementing the project. You can find it here.

If you want to use pretrained weights for LSTM model. You can download them here.

Flickr8k dataset can be downloaded here.

Results:

upload_2 upload_1 Sometimes beam search do great job. upload_3

Dependencies:

  • Keras 2.1.6
  • Tensorflow 1.7.0
  • Numpy
  • Pandas
  • Pickle
  • PIL
  • Tqdm

Note : It is recommended to use above mentioned version of Keras and Tensorflow.

References

1)CS231n Winter 2016 Lesson 10 Recurrent Neural Networks, Image Captioning and LSTM

2)Another implementation of image captioning model.

image-captioning's People

Contributors

faizan-e-mustafa avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.