Skip to content

Latest commit

 

History

History
59 lines (43 loc) · 2.41 KB

File metadata and controls

59 lines (43 loc) · 2.41 KB

DEVELOPERS AREA

Image Captioning Project

In this project, we design and train a CNN-RNN (Convolutional Neural Network - Recurrent Neural Network) model for automatically generating image captions. The network is trained on the Microsoft Common Objects in COntext (MS COCO) dataset.

Welcome

How to setup the project locally

In order to work on this project locally we have to configure it to our base system and configure it to paths that are required by the project

How to install the project

After we ready with setup we need to install the project with given requirements of the packages and modules in the local system. Once the installation is complete we can run over project

  • Install the requirements using the command

pip install -r requirements.txt

  • Then open the following files in Jupyter Notebook

0_Dataset.ipynb 1_Preliminaries.ipynb 2_Training.ipynb 3_Inference.ipynb

How to run the project after setup

When done with the Setup and Installation process it time to test our project and run it locally in your system.

We need to test these Python files by running them on command prompt.

python data_loader.py
python model.py
python vocabulary.py

Contribution

If you’re interested in the project, feel free to open an issue, create a PR, or just come say hi and tell us more about yourself.

  1. Fork it (https://github.com/sauravraghuvanshi/Udacity-Computer-Vision-Nanodegree-Program)
  2. Clone it ( https://github.com/sauravraghuvanshi/Udacity-Computer-Vision-Nanodegree-Program.git )
  3. Create your feature branch ( git checkout -b feature/fooBar )
  4. Commit your changes ( git commit -am 'Add some fooBar' )
  5. Push to the branch ( git push origin feature/fooBar )
  6. Create a new Pull Request