From the course: Grasshopper: Tips, Tricks, and Techniques

Unlock this course with a free trial

Join today to access over 22,400 courses taught by industry experts.

Prep the neural network in Crow

Prep the neural network in Crow

- [Instructor] Welcome, this is the third in a series of five videos that focus on machine learning and artificial intelligence within Grasshopper 3D. So we are setting up our neural network to recognize the features of faces. So we want to be able to recognize the different parts of the face, so we can orient new scanned faces in order fit mask geometry onto the face. So in the last video we set up a cluster that converts a face mesh into sets of nine numbers that describe each face. So each face will be classified based on where it is on the face and the classification will be done based on the description that has those nine numbers in it. Basically a nine-dimensional vector. In order to do that we need to tell our neural network that we're going to train which face is which for training purposes and then it will classify things on its own. So we're going to set up that classification and that's the trainOut input in…

Contents