Creating an Object Detection Pipeline for GPUs

Originally published at: Creating an Object Detection Pipeline for GPUs | NVIDIA Technical Blog

Earlier this year in March, we showed retinanet-examples, an open source example of how to accelerate the training and deployment of an object detection pipeline for GPUs. We presented the project at NVIDIA’s GPU Technology Conference in San Jose. This post discusses the motivation for this work, a high-level description of the architecture, and a brief look…