Multi-label classification is a useful functionality of deep neural networks. I recently added this functionality into Keras' ImageDataGenerator
in order to train on data that does not fit into memory. This blog post shows the functionality and runs over a complete example using the VOC2012 dataset.
Part of the core development team of the keras preprocessing component of the Keras framework.
Read moreAs a consultant from GoDataDriven working as the data lead for Schiphol Royal Group.
Read moreGave a free 3 hour workshop about transfer learning.
Read morePresented Operation Tulip: Using Deep Learning Models to Automate Auction Processes.
Read moreTook a 2 day course of Unsupervised and Reinforcement Learning in San Francisco.
Read moreGave a deep learning introductory workshop to Keras.
Read moreAs a consultant from GoDataDriven working as a lead data scientist for the Nspire project in KPN.
Read moreGave a free 3 hour workshop about deep learning.
Read moreTook a 2 day course of advanced deep learning with Python & Tensorflow in San Francisco.
Read moreStarted working as a data scientist for GoDataDriven.
Read moreGave a face recognition workshop with opencv and tensorflow.
Read more