Model Information
Source model
- Input shape: 640x640
- Number of parameters: 11.27M
- Model size: 45.22M
- Output shape: 1x32x160x160, 1x116x8400
Source model repository: yolov8
Converted model
- Precision: W8A16
- Backend: QNN2.16
- Target Device: SNM972 QCS8550
Inference with AidLite SDK
SDK installation
Model Farm uses AidLite SDK as the model inference SDK. For details, please refer to the AidLite Developer Documentation
- Install AidLite SDK
# Install the appropriate version of the aidlite sdk
sudo aid-pkg update
sudo aid-pkg install aidlite-sdk
# Download the qnn version that matches the above backend. Eg Install QNN2.23 Aidlite: sudo aid-pkg install aidlite-qnn223
sudo aid-pkg install aidlite-{QNN VERSION}
- Verify AidLite SDK
# aidlite sdk c++ check
python3 -c "import aidlite ; print(aidlite.get_library_version())"
# aidlite sdk python check
python3 -c "import aidlite ; print(aidlite.get_py_library_version())"
Run demo
python
cd yolov8s_seg/model_farm_yolov8s_seg_qsc8550_qnn2.16_int16_aidlite
python3 ./python/run_test.py --target_model ./models/cutoff_yolov8s-seg_w8a16.qnn216.ctx.bin --imgs ./python/bus.jpg --invoke_nums 10
cpp
cd yolov8s_seg/model_farm_yolov8s_seg_qsc8550_qnn2.16_int16_aidlite/cpp
mkdir build && cd build
cmake ..
make
./run_test