Meta Tagging Shoes with Pytorch CNNs – Towards Data Science

Something that I have been wanting to play around with is generating text to describe images. When posed in this way two pathways come to mind. First would be to use a combination of CNNs for feature extraction and feed those extracted features to an LSTM and let it generate descriptions by iterating repeatedly. The second way would be to build a multi-label classification model and have the output nodes represent specific tags. The first model is good in the case you wanted to generate captions for images that have a grammatical structure to them.