hadryan/tensorrtintegrate

TensorRT ONNX Plugin、Inference、Compile

TensorRT-Integrate

1. Support pytorch onnx plugin（DCN、HSwish ... etc.）
2. Simpler inference and plugin APIs

Re-implement

CenterNet : ctdet_coco_dla_2x

CenterTrack: coco_tracking

• coco_tracking.onnx download

• nuScenes_3Dtracking.onnx download

DBFace

Use TensorRT-Integrate

install protobuf >= v3.8.x

bash getDLADCN.sh
make run -j32

Inference Code

auto engine = TRTInfer::loadEngine("models/efficientnet-b0.fp32.trtmodel");
float mean[3] = {0.485, 0.456, 0.406};
float std[3] = {0.229, 0.224, 0.225};
Mat image = imread("img.jpg");
engine->input()->setNormMat(0, image, mean, std);
engine->forward();
engine->output(0)->print();

Environment

• tensorRT7.0.0.11
• opencv3.4.6
• cudnn7.6.3
• cuda10.0
• protobuf v3.8.x
• Visual Studio 2017
• lean-windows.zip (include tensorRT、opencv、cudnn、cuda、protobuf)

Plugin

1. Pytorch export ONNX: plugin_onnx_export.py
2. MReLU.cu 、HSwish.cu、DCNv2.cu