Supported Modules#

The table below shows all the current supported modules which are integrated in pyppbox in many different ways. The main idea of the integrations is to make them fully compatible with our PoseTReID framework read more here. Thus, not every original feature of every supported module is fully functioning as it was made. For example, the supported YOLO_Classic / YOLO module in the table can only be used as a detector (Inference/Prediction) using the native or official `.weights` files, but it can’t do any custom data traning, etc.

Modules	General Name	Config Name	Details
Detectors	YOLO	YOLO_Classic	* Built-in by using OpenCV DNN * Model: .weights V2, V3, V4 * Run on: CPU or GPU (OpenCV DNN)
Detectors	YOLO	YOLO_Ultralytics	* Integrated by linking ultralytics * Model: .pt V3, V5, V8, V9, v10, v11 * Run on: CPU or GPU (PyTorch)
Trackers	Centroid	Centroid	* Built-in / Native * Run on: CPU
	SORT	SORT	* Integrated by embedding * SORT repo * Run on: CPU
	DeepSORT	DeepSORT	* Integrated by embedding * DeepSORT repo * Run on: CPU or GPU (Tensorflow)
ReIDers	FaceNet	FaceNet	* Integrated by embedding * FaceNet repo * Run on: CPU or GPU (Tensorflow)
ReIDers	Torchreid	Torchreid	* Integrated by linking pyppbox-torchreid * Model: OSNet-AIN, OSNet, MLFN * Run on: CPU or GPU (PyTorch)