Object Detection and Semantic Segmentation Workshop

The following notebook is the end result of the Mask RCNN implementation for object detection and semantic segmentation. Scroll down to see three other notebooks that explain how the end result was obtained.

This notebook visualizes the different pre-processing steps to prepare the training data.

This notebook goes in depth into the steps performed to detect and segment objects. It provides visualizations of every step of the pipeline.

This notebooks inspects the weights of a trained model and looks for anomalies and odd patterns.