The tutorial is the workflow from labeling objects (using vott), building a object detection model in tensorflow, training it locally ... In TF_ObjectDetection_Flow, the directionary raw/origindata ...

With a plethora of object detection models available ranging from ... enough to learn patterns from P&ID symbols just by using 5 training images.

It also contains Python scripts that are used to generate the training data. It has scripts to test out the object detection classifier on images, videos, or a webcam feed. You can ignore the \doc ...

Abstract: Small object detection, especially for fast-moving ... while preserving critical information and improving gradient flow behavior in the shallow layers by utilizing auxiliary training ...