AI Image Caption Generator

Deep Learning & Web Deployment

Of Interest: End-to-end deep learning model with a real-time web interface

Project Overview

The primary goal was to build an end-to-end deep learning model that could automatically generate descriptive captions for images. This involved combining a Convolutional Neural Network (CNN) for image feature extraction with a Recurrent Neural Network (RNN), specifically an LSTM, for sequence generation.

1.1

Overview

This project involved developing an end-to-end deep learning model to generate natural language captions for images. The core of the project was a CNN + LSTM architecture built in TensorFlow, designed to accurately describe the contents of a given image.

2.1

Technical Stack

The model was deployed as a web service with a user-friendly frontend to allow for real-time interaction.

  • Deep Learning: TensorFlow, Python
  • Backend & Deployment: Flask, Google Cloud
  • Frontend: React