The neural network learned how to create complex images by text description

Researchers have developed a generative adversarial neural network that is very similar to the one presented.

formerly Microsoft AttGAN algorithm.The difference is that the new neural network is object-oriented when creating images based on text - in other words, it analyzes the desired text and lays out objects from the library on the finished image.

The algorithm was trained on 328 thousand objects with text description collected in COCO dataset.

The study says that the presented neural network copes better with the creation of text-based description of complex objects that contain many small details.

Earlier, Facebook AI laboratory introduced artificial intelligence, which can generate a recipe for this dish from food photos.