In this project, I trained a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) with several stacked Long-Short Term Memory (LSTM) model layers on the MS-COCO dataset to effectively generate captions for any reasonable image.
roshanr11/image-captioning
Used deep learning to train a CNN + RNN/LSTM on the MS-COCO dataset to automatically generate captions.
HTML