Image-captioning

This is a deep learning model used to predict the captions for images. In this model Inception_v3 and lstm network is used in combination the input for the inception _v3 model is a image of size(299,299) and the input for the LSTM network is a caption of the image from the Training set and the outputs of these networks are fed in to a neural network to predict the probabilities of next occuring word in a caption The dataset used is flickr_8k