Basic AI Inference Examples

YOLOv5 Object Detection (Official Example)

# Enter official sample directory
cd /usr/local/share/aidlite/examples/aidlite_qnn236/cpp
# Run with DSP acceleration (recommended, argument 3 for .bin model, argument 4 for .so model)
LD_PRELOAD=/usr/lib/libstdc++.so.6.0.30 ./qnn_yolov5_multi 3

Expected output:

classid: 0, score 0.812817, pos ([115.072533], [236.646347]) ([202.021912], [541.845459])
classid: 0, score 0.789807, pos ([211.840363], [246.274216]) ([283.799805], [514.897522])
classid: 0, score 0.785955, pos ([472.021393], [233.328232]) ([561.091858], [520.786987])

Python YOLOv5 Inference

# Python sample creates files, while / partition is read-only at this stage
cp /usr/local/share/aidlite/examples/aidlite_qnn236 -r /data
cd /data/aidlite_qnn236/python
LD_PRELOAD=/usr/lib/libstdc++.so.6.0.30 python3 qnn_yolov5_multi.py 3

Verification: check generated qnn_yolov5_multi_pil.jpg and confirm detection boxes are correct.