backbone |
input_size |
GPU |
mode |
inference Time |
mobilenetv2 |
512x512 |
gtx 1070 |
float32 |
3.798ms |
mobilenetv2 |
512x512 |
jetson TX2 |
float16 |
22ms |
- gtx 1070
- jetson TX2
- Convert CenterNet model to onnx (deform conv is not support)
- Use netron to observe whether the output of the converted onnx model is (hm, reg, wh)
git clone https://github.com/CaoWGG/TensorRT-CenterNet.git
cd TensorRT-CenterNet
mkdir build
cd build && cmake .. && make
cd ..
##cthelmet
./buildEngine -i model/ctdet_helmet.onnx -o model/ctdet_helmet.engine
./runDet -e model/ctdet_helmet.engine -i test.jpg -c test.h264
##centerface
./buildEngine -i model/centerface.onnx -o model/centerface.engine
./runDet -e model/centerface.engine -i test.jpg -c test.h264
## a simple python demo (need cv2 numpy)
python3 run.py