Using NumPy To Optimize Object Detection

This is Part 4 of our ongoing series on NumPy optimization. In Parts 1 and 2 we covered the concepts of vectorization and broadcasting, and how they can be applied to optimize an implementation of the K-Means clustering algorithm. Next in the cue, Part 3 covered important concepts like strides, reshape, and transpose in NumPy. In this post, Part 4, we'll cover the application of those concepts to speed up a deep learning-based object detector: YOLO. Here are the links to the earlier parts for your reference.