Using Machine Learning to generate captions for Images

The first and foremost step of any Machine Learning Program is to clean the data and get rid of any unwanted data. As we are dealing with text data in the captions, we will perform basic cleaning steps like converting all letters to lowercase as for a computer'Hey' and'hey' are two completely different words, removing special tokens and punctuation marks such as *, (, £, $, %, etc, and eliminating any words that contain numbers. We first create a vocabulary for all the unique in our dataset i.e, 8000 (no. of pictures) * 5 ( captions for each image) 40000 captions. We found that to be equal to 8763. But most of these words occurred just one or two times and we would not want them in our model as it will not make our model robust to outliers. Hence we set a threshold of 10 minimum occurrences of a word to be included in our vocabulary and that turns out to be equal to 1652 unique words.