STM32 Edge NPU Vision & MLOps Pipeline

PythonYOLOv8nOpenCVONNX RuntimeTFLite INT8STM32MP257 NPUOpenSTLinuxX-LINUX-AI
STM32 Edge NPU Vision & MLOps Pipeline preview

overview.

Built to run real-time physical board-state perception on the STM32MP257F-DK's 1.35 TOPS Neural Processing Unit under OpenSTLinux rather than a desktop GPU. A classical OpenCV stage detects the board via Canny edges and adaptive thresholding, applies a 320x320 homography warp with EMA corner stabilization, and feeds a custom-trained YOLOv8n detector backed by per-cell temporal voting. A unified inference wrapper runs PyTorch (.pt), ONNX Runtime with VSINPUExecutionProvider (.onnx), TFLite with libvx_delegate INT8 (.tflite), and ST Neural Binary Graph (.nb) models. Around the detector sits an automated, resumable 11-stage MLOps web dashboard covering dataset validation, augmentation, training, evaluation, ONNX opset-12 export, INT8 post-training quantization, ST Edge AI Developer Cloud compilation, SSH deployment, on-board CMA/latency verification, and report generation.

key features.

  • 0.998 precision, 1.000 recall, 0.995 mAP@0.5, and 100% cell-level accuracy across 449 held-out cells
  • INT8 post-training quantization and NPU compilation shrinking weights from 6.22 MB (FP32) to 3.10 MB (TFLite INT8) and 2.68 MB (.nb NPU binary)
  • Resumable 11-stage MLOps web dashboard automating dataset scan, training, PTQ calibration, ST Edge AI Cloud compilation, and SSH board deployment

screenshots.

MLOps pipeline benchmark results across FP32, ONNX, and TFLite INT8 backends

11-stage MLOps pipeline evaluation results and backend latency comparison

STM32MP257 Edge NPU Vision system architecture

End-to-end architecture from camera homography warp to STM32MP257 NPU inference