Deep Learning model for generating captions for a given image.

• Trained on 30K Images from Flickr
• Build over pre-trained InceptionV3 model and GloVe
• Used Word Embedding with Convolutional Neural Net and Recurrent Neural Net to generate results.
• Greedy Searching for searching next best suited word.
• Weights

Greedy: A group of men dancing in front of a crowd

Greedy: A dog is running through the grass

Greedy: A group of people is walking on the street