I am a BIM Manager working with computational design and machine learning. Since 2 years I have been working as a BIM Manager at BPA Architecture. My role is to develop and organise all BIM Protocols, Libraries and procedures for the office. Our company has a plug-in plug-in written by me for Revit. Currently, the processing capacity of this plug-in has been increased with Machine Learning. I am also the author of the "Shapely" package in Revit-Dynamo. This Dynamo package is designed to help us manipulate 2D geometries. Currently, this Dynamo package can work with Machine Learning, so that our projects can be used directly with Machine Learning training models.
What to expect during the event
With the developing technology, we see that Machine Learning is widely used in almost all sectors. So can a vector-based digital design programmes work with Machine Learning? The answer to this question is a definite "Yes". To use machine learning in digital design programmes, you need to transform the data. Today we use the "Shapely" package for this data transformation. The "Shapely geometry" package not only allows users to manipulate 2D geometries, but also integrates seamlessly with ML.
But how does Shapely do that with ML?
In order to work with ML, you do need Numpy. Unfortunately, you cannot directly use Dynamo geometries within an ML model. This is where « Shapely geometry » comes into play. It allows you to perform these operations directly using Numpy, making it a valuable tool for integrating geometry operations into your ML workflows. Meaning, we need to first convert any 2D geometry into « Shapely geometry » and then into 'Numpy' data. Don't worry, we don't lose any data during all these conversions. In summary, we are transforming the geometry into another format without losing any data. This is truly a very functional and flexible data interchange.
Machine Learning, Revit,Dynamo,ShapelyGeometry
Machine Learning in Building Design