faq

# faq
Error Code 1: Internal Error (Unsupported SM: 0x809)
The architecture of the higher version does not support the use of the earlier version of TensorRT,
and you need to upgrade the TensorRT version

git clone https://github.com/THU-MIG/yolov10.git
cd yolov10/
wget https://github.com/THU-MIG/yolov10/releases/download/v1.1/yolov10n.pt

git clone https://github.com/wang-xinyu/tensorrtx.git
cp [PATH-TO-TENSORRTX]/yolov10/gen_wts.py .

python gen_wts.py -w yolov10n.pt -o yolov10n.wts

# A file 'yolov10n.wts' will be generated.

cd [PATH-TO-TENSORRTX]/yolov10


# add test images
mkdir images
cp [PATH-TO-TENSORRTX]/yolov3-spp/samples/*.jpg ./images


# Update kNumClass in src/config.h if your model is trained on custom dataset
mkdir build
cd build
cp [PATH-TO-yolov10]/yolov10n.wts .
cmake ..
make


# Build and serialize TensorRT engine
./yolov10_det -s yolov10n.wts yolov10n.engine [n/s/m/b/l/x]


# Run inference
./yolov10_det -d yolov10n.engine ../images

# The results are displayed in the console

// Install python-tensorrt, pycuda, etc.
// Ensure the yolov10n.engine
python yolov10_det_trt.py ./build/yolov10n.engine ./build/libmyplugins.so