Tiki AI -- A virtual Assistant for VQA

Is Tiki an optimist or pessimist? Do I need to get my baby from crib? Initialization of the model takes 16 seconds on a V100, with inference taking 1.5 seconds. Due to the cost of running the V100 server, the machine is no longer running. We also run a flask server that accepts wave files that are then sent to the Google Cloud for interpretation. Visual question answering (VQA) is a new field that combines both computer vision and NLP to provide answers to simple questions using common human syntax.