convert mmpose model to ONNX for TensorRT about mmpose HOT 8 CLOSED

this will be added to the next iteration, with great possibility

from mmpose.

That would be fantastic. I can help implement C++ inference code using TensorRT, for the bottom-up approach.

from mmpose.

maybe this pr open-mmlab/mmaction2#160 is helpful

from mmpose.

from mmpose.

Hi @khanhha , you can try this pull request #305, any feedback would be great

from mmpose.

I find the bottom-up approach have the matrix algorithm.
Do you have any idea for implement C++ inference code

from mmpose.

np & torch can be very fast for matrix things. Mostly there is no need for c++ reimplementation. Could you please open a new issue giving details on where is the slowness? We will try to optimize it once the bottleneck is clear

from mmpose.

Hi @khanhha ,
Do you have any idea for implement C++ inference code for buttom-up?
This project only have top-down
https://github.com/linghu8812/tensorrt_inference/tree/master/mmpose

from mmpose.