Skip to content

ReuveniDor/Caption_RNN_Study

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image Captioning Project

This project aims to develop image captioning models using recurrent neural networks (RNNs) and attention mechanisms used in LSTM. The models are trained on the COCO dataset, a large-scale dataset of images with corresponding captions.

Table of Contents

Project Description

The project consists of the following components:

  • Data downloading and preprocessing
  • Minibatch visualization
  • Overfitting test
  • RNN model training
  • Attention LSTM model training
  • Result visualization

How to Run the Project

To run the project, follow these steps:

  1. Install the required dependencies.
  2. Clone the repository.
  3. Download coco.py and save in datasets directory
  4. Use the ipynb notebook to train the models and show the result.

Results

image image

image image

We can clearly see that the results on the train data are much better then on the val data.

Badges

  • License

Conclusion

This project provided a comprehensive overview of image captioning models and their implementation. The user gained hands-on experience with data preprocessing, model training, and result visualization. The project also highlighted the importance of attention mechanisms in improving the performance of image captioning models.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published