dai.node.NeuralNetwork, dai.node.DetectionParser, dai.node.YoloDetectionNetwork

Thor

depthai-python/examples/NeuralNetwork/detection_parser.py that seems to be updated uses:
nn = pipeline.create(dai.node.NeuralNetwork)
det = pipeline.create(dai.node.DetectionParser)

What is the difference if any with using
dai.node.YoloDetectionNetwork instead of the above two?

I'm looking for the most accurate way of doing it.....
btw the documentation on the web doesn't seem to be really accurate anymore, at least looking at the options listed for .DetectionParser hint: it is not even listed as a node

jakaskerl

Hi @Thor
No difference really. The YoloDetectionNetwork is just a two-in-one type of node. It's not meant to be used as a node, so it is not added to the docs. Keep using the YoloDetectionNetwork and MobilenetDetectionNetwork, it works the same way.

Thanks,
Jaka