search

marcoslucianops / DeepStream-Yolo

NVIDIA DeepStream SDK 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
MIT License
1.45k stars 357 forks source link

Why ONNX? #365

Closed OctaM closed 1 year ago

OctaM commented 1 year ago

It's not an actual issue. But i'm just curious why it was changed to .onnx from .wts & .cfg? Is it a performance improvement?

marcoslucianops commented 1 year ago

Because it's easier to use any model in the DeepStream. It has a native ONNX parser, so I don't need to create the conversor layer by layer.

OctaM commented 1 year ago

Cool, thanks for your answer!

marcoslucianops commented 1 year ago

I forgot to say, but the speed and accuracy between both methods are equal.