Coder Social home page Coder Social logo

ntrang086 / image_captioning Goto Github PK

View Code? Open in Web Editor NEW
71.0 6.0 42.0 3.63 MB

generate captions for images using a CNN-RNN model that is trained on the Microsoft Common Objects in COntext (MS COCO) dataset

License: MIT License

Python 100.00%
image-captioning rnn-model cnn mscoco pytorch nlp computer-vision encoder-decoder

image_captioning's People

Contributors

ntrang086 avatar

Stargazers

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

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

image_captioning's Issues

How do I get captions for Images in my computer with any annoattions?

Hello Trang!! All your work is appreciable. I tried contacting you on LinkedIn as well. I have trained the model and have the model files. The captions are generated for test images ( code cells after embedded features cell is executing). Please tell the approach how do I test real world images with the help of model files I have. I will be very thankful if you help me out with this !!
Even the test images are taking the annotations, how do i get captions for images without any annotations fed in?

Please tell me how do I apply to real world images (i.e. Images on my computer )

I dont know what to do first

Sorry, cause I am poor about programming.. so i want you to teach me about the process of
doing this well..
As i see.. 1. download the dataset and api
2. running the code using zupiter notebook
3. input image to code
Is it right?
But actually i dont know the process of writting the code .. threre are too many codes you uploded ..
Is there full code that i can use?

Pre - trained model

Can u provide me the,

train-model-712900.pkl
model-6.pkl
best-model.pkl

val-model-76333.pkl
train-model-7.pkl
best-model.pkl

Attention in the model?

Hi. You mentioned that your implementation includes: Show, Attend and Tell.
But I don't see any Attention implementation in your code. So may I know if your code does provide Attention mechanism in any place? And is it possible you can upload the trained models also?

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.