Summary

In this implementation, we used a pretrained Inception-v3 model as a feature extractor in an encoder trained on the ImageNet dataset as part of a deep learning solution. This solution combines current state-of-the-art techniques in both computer vision and natural language processing, to form a complete image description approach (https://www.cs.cmu.edu/~afarhadi/papers/sentence.pdf) able to construct computer-generated natural descriptions of any provided images. We've effectively broken the barrier between images and language with this trained model and we've provided a technology that could be used as part of an application, helping the visually impaired enjoy the benefits of the megatrend of photo sharing! Great work!