keilabcs/image-captioning

Implemented 3 different architectures to tackle the Image Caption problem, i.e, Merged Encoder-Decoder - Bahdanau Attention - Transformers

Image Captioning Overview

In recent years, neural networks have fueled dramatic advances in image captioning. Researchers are looking for more challenging applications for computer vision and Sequence to Sequence modeling systems. They seek to describe the world in human terms. I have implemented three different architectures from simple Encoder Decoders to Transformers with Multi-Head Attention.

Datasets :-

1. Flickr8K
2. Glove6B

My Articles

1. Create your Own Image Caption Generator using Keras!
2. A Hands-on Tutorial to Learn Attention Mechanism For Image Caption Generation in Python
3. Implementation of Attention Mechanism for Caption Generation on Transformers using TensorFlow