Open-Source Projects
Mask R-CNN for Object Detection and Segmentation on Keras and TensorFlow
An implementation of Mask RCNN on Keras and TensorFlow. I built this during my work at Matterport and they graciously agreed to open source it. Since its release in November 2017, it has become one of the top instance segmentation models on TensorFlow and was used by thousands of developers in applications ranging from Kaggle competitions to Ph.D theses.
HiddenLayer: Neural Network Visualization and Monitoring
Like TensorBoard, but simpler and runs directly in Jupyter notebook. It was recently adopted by Microsoft as one of the building blocks of their recently released TensorWatch tool. Supports PyTorch, TensorFlow, and Keras.
Deep Learning Docker Container
To clean up my own development environment, I built a Docker container that includes recent versions of the top deep learning tools. Getting everything to work smoothly took a bit of work, so I shared it publicly on Docker Hub for others to use. It's currently the #1 container and most starred on DockerHub when you search for deep learning containers.
Talks and Articles
Traffic Sign Recognition with TensorFlow
I occasionally talk about deep learning at local events. This is a talk I did for ACM (Association for Computing Machinery) about using TensorFlow to recognize traffic signs.
Splash of Color: Instance Segmentation with Mask R-CNN and TensorFlow
A question I kept getting about my Mask RCNN implementation was: how do I use it with my own dataset? So I built a toy example and documented the whole process, including manually annotating a small dataset from scratch. The restul was an article and code to automatically apply a color splash effect on images of balloons (i.e. convert the image to grayscale except for balloons, which stay colored).
