The author of the AI Weirdness blog Janelle Shane had discovered the generative-controversial neural network called AttnGAN, which is trained to draw images on the text description. The problem is that it requires too accurately defined picture parameters and sometimes can not determine the boundaries of objects.
Janelle notes that, while the neural network was trained on a narrow set of data in the form of birds, it obtained nice images:
However, when the creators trained it on a dataset that included pictures from sheep to shopping centers, it could not create a meaningful image in a similar way. The author of AI Weirdness believes that the error lies in too wide a set of initial data, in which AttnGAN could not select the appropriate instances:
In addition, it somehow has a problem with determining the correct number of holes on the human face. Developers AttnGAN added to the control dataset person celebrities to create photorealistic portraits, but the neural network couldn't do that:
Additionally, neural network is real bad at displaying animals:
Janelle Shane calls the project AttnGAN "Visual Chatbot on the contrary." This chat bot analyzes the image that the user sends and describes it, often implausibly.