instance segmentation support/example using C API

[tehkillerbee]

Describe the feature
Instance segmentation does not appear to be supported by the C API at this point. This would be a very welcome addition.

Motivation
I looked at the MMDeploy SDK C code and noticed that the examples do not cover Instance segmentation.

However, it is possible to deploy a model for instance segmentation (Mask RCNN) using TensorRT backend. The resulting TensorRT model works correctly. Visualizing the output shows identical output for PyTorch/TensorRT (albeit with incorrect CLASSES, since I use custom classes). Running the same model with the "object_detection.cpp" does work, although with no masks.

If this feature is already supported internally by the C API, feel free to point me in the right direction so I can make an example application myself.

[lvhan028]

Hi, @tehkillerbee. Please refer to detector.h. It supports both object detection and instance segmentation.

[tehkillerbee]

@lvhan028 Thank you for your advice, I managed to get it working - I should've looked closer in detector.h. Should I update the object_detection.cpp example accordingly or should I add a separate instance segmentation example?

[lvhan028]

I think it's better to update object_detection.cpp. For one thing, it is consistent with the header file , for another the user document won't be changed:)

[tehkillerbee]

Ok! I need to make sure the example still works with mmdetection models that does not use mask output. Can I assume that "bboxes[i].mask" will be a nullptr, if the mask is not used?

[lvhan028]

Ok! I need to make sure the example still works with mmdetection models that does not use mask output. Can I assume that "bboxes[i].mask" will be a nullptr, if the mask is not used?

sure

[lvhan028]

pr #55