Image Caption

This repository contains a production grade machine learning model served by tensorflow-serving and flask which performs image captioning with a front end interface designed with React.

Key Features

• User-friendly web interface for uploading images.
• Backend powered by Flask, enabling seamless communication with the deep learning model.
• The deep learning model is built using Keras, leveraging pre-trained convolutional neural networks (CNN) and recurrent neural networks (RNN) for image feature extraction and caption generation, respectively.
• Dockerized the entire application for installability
• Real-time image processing and caption generation.
• Easy-to-understand UI built with React, allowing a smooth user experience.

Installation

1. Run git clone https://github.com/mohitpg/ImageCaption.git
   
2. Go to the folder ImageCaption.
   
3. Run docker-compose up.
   
4. The application can be accessed at localhost:5000

Acknowledgements

The model architecture and training code were adapted from Harshall Lamba's Article

Screenshots