Rockchip RKNN

RKNN-Toolkit2, RKNN-Toolkit-Lite2 and the C runtime API.

RKNN-Toolkit2 runs on an x86 Linux host and converts ONNX, TFLite, PyTorch and other models to .rknn, with INT8 quantisation. On the board you run models with RKNN-Toolkit-Lite2 (Python) or the C API (librknnrt). Older RV1109/RV1126 SDKs use the original RKNN-Toolkit (v1).

Key points

Quantise with a representative dataset (a dataset.txt listing 20–200 real images).
Match mean/std normalisation in rknn.config() to what the model was trained with.
Use accuracy_analysis() to find layers that lose precision after quantisation.

References

RKNN guides

AI 与 NPU中级

Convert YOLO to RKNN and Run It on the RK3588 NPU

Export YOLO to ONNX, quantise and convert it to .rknn with RKNN-Toolkit2 on an x86 host, then run it on the board with RKNN-Toolkit-Lite2, using all three RK3588 NPU cores.

10 分钟阅读 · RK3588, RK3588S, RK3576

发现错误或有补充？提出改进建议.

正在开发瑞芯微产品？

从硬件设计到 Linux、Android 与 AI 集成，为你的瑞芯微项目提供工程支持。

申请工程支持了解我们的服务