> One practical detail is worth knowing. The new engine is CPU-only at the moment, so if you select a non-CPU backend and target (for example CUDA or OpenVINO through setPreferableBackend and setPreferableTarget), you will want the classic engine.
So there's room for even better performance!
It's certainly a choice to make your headline feature a new ONNX engine, feature a bunch of comparisons how it's better than ONNXRuntime, while casually mentioning on the side that the cool new much faster engine is CPU-only
Sure, running models on the CPU is very much a thing in computer vision (the benchmarked YOLOv8n has 37M params). But this whole announcement feels more like OpenCV catching up to the modern world, not "The Biggest Leap in Years for Computer Vision"
Still great, needing fewer libraries is a good thing, but maybe a bit oversold
loading story #48458383
No one uses ONNXRuntime (nor the new engine in OpenCV 5) in production. For anything performance-sensitive, one would run models under TensorRT, as an example.
loading story #48458538
loading story #48458423
how are supposed to use TensorRT on iOS, iPadOS, Android or even Web? Production is not only cloud.
loading story #48458885
loading story #48458335
loading story #48459976
loading story #48460228
loading story #48460749