Detection model without onnxruntime

[johngebbie]

Hi @emilianavt,
I'm just using opencv without onnxruntime and got the landmarking working using the unoptimized models you shared in #48, which is great.

I just tried the optimized detection model (mnv3_detection_opt.onnx) but not that surprisingly got the same layer error as with the optimized landmarking models.

It'd be fab if you could share the unoptimized detection model too.

[Emiliana]

Please try this: mnv3_detection.zip

[johngebbie]

It loads successfully. You're a star!