Task: with input is photo, model predict text wich the content in photo
Tool, model and framework: keras, InmageNet model, LSTM, Glove
https://nttuan8.com/bai-15-ung-dung-them-mo-ta-cho-anh-image-captioning/
https://www.analyticsvidhya.com/blog/2020/11/create-your-own-image-caption-generator-using-keras/

