Lab Assignment 11 - Achu0015/BigDataAna-App-SP2K17 GitHub Wiki

                                         # Lab Assignment 11

In this lab we wrote Tensorflow program to generate captions for the images.

In this lab we used show and tell model, where give input as images and we produce the captions for the images.

This is possible through a model of RNN which is known as LSTM (Long Short Term Memory) and with the show and tell model, we use encoding an image into fixed length vector representation and again decoding the vector representation to natural language.

The two images I have used for input are shown below, followed by the captions generated by our model:

The captions for the above images are generated as shown below: