Now, i used yolo11 module ,
cd /opt/ST/STEdgeAI/2.2/Utilities/linux/
./stedgeai generate -m /home/alientek/STM32MPU_workspace/yolo11.onnx --target stm32mp25
and get yolo11.nb file
in the my stm32mp2 broad.
x-linux-ai-benchmark -m ./yolo11n.nb
╔════════════════════════════════════════════════╗
║ X-LINUX-AI unified NN model benchmark ║
╠════════════════════════════════╦═══════════════╣
║ Machine ║ STM32MP257 ║
║ CPU cores ║ 2 ║
║ CPU Clock frequency ║ 1.5GHz ║
║ GPU/NPU Driver Version ║ 6.4.19 ║
║ GPU/NPU Clock frequency ║ 800 MHZ ║
║ X-LINUX-AI Version ║ v6.0.0 ║
║ ║ ║
║ ║ ║
╚════════════════════════════════╩═══════════════╝
For hardware accelerated models, computation engine used for benchmark is NPU running at 800 MHZ
For other models, computation engine uses for benchmark is CPU with 2 cores at : 1.5GHz
╔══════════════════════════════════════════════════════════════════════════╗
║ NBG models benchmark ║
╠════════════╦═════════════════════╦═══════╦═══════╦═══════╦═══════════════╣
║ Model Name ║ Inference Time (ms) ║ CPU % ║ GPU % ║ NPU % ║ Peak RAM (MB) ║
╠════════════╬═════════════════════╬═══════╬═══════╬═══════╬═══════════════╣
║ yolo11n ║ 1043.37 ║ 0.0 ║ 96.23 ║ 3.77 ║ 30.02 ║
╚════════════╩═════════════════════╩═══════╩═══════╩═══════╩═══════════════╝
╔══════════════════════════════════════════════════════════════╗
║ Non-Optimal models ║
╠════════════╦═════════════════════════════════════════════════╣
║ model name ║ comments ║
╠════════════╬═════════════════════════════════════════════════╣
║ yolo11n ║ GPU usage is 96.23% compared to NPU usage 3.77% ║
║ ║ please verify if the model is quantized or that ║
║ ║ the quantization scheme used is the 8-bits per- ║
║ ║ tensor ║
╚════════════╩═════════════════════════════════════════════════╝
the Inference Time is 1043.37 ms.
