Image-caption Using End2end CNN , LSTM based Model!

The aim of the project is to generate a caption for images.
Each image has a story, Image Captioning narrates it.

this model is bases on Show and Tell: A Neural Image Caption Generator

📖 Documentation

How to Run

Install the requirements:

pip3 install -r requirements.txt 

Running the Model

python3 model.py

Results

The results are not bad at all! a lot of test cases gonna be so realistic, but the model still needs more training

Paper

This project is an implementation of the Show and Tell, published 2015.

Dataset

• Dataset used is Flicker8k each image have 5 captions.
• you can request data from here [Flicker8k] (https://forms.illinois.edu/sec/1713398).
  Sample of the data used

Model Used

Experiments

Future Work

-Training, Training and more Training
-Using Resnet instead of VGG16
-Creating API for production level
-Using Word2Vec embedding.