search

CarkusL / CenterPoint

Export CenterPoint PonintPillars ONNX Model For TensorRT
MIT License
204 stars 50 forks source link

centerhead decode #26

Open realwenpeng opened 11 months ago

realwenpeng commented 11 months ago

I want to know why the centerhead onnx do not contain decode part. If I make the centerhead decode part into tensorrt *.engine, how it would infulence the inference speed.

CarkusL commented 10 months ago

I think placing the decode part in .engine file can speed up model inference. You can try it.