Article library
Includes platform references; association does not mean hardware validation. Check each article’s SoC, BSP and interface requirements.
363 articles · Page 1
RK3572: 8nm, eight cores and 4 TOPS AI — ArmSoM plans a Zero-form-factor board
Rockchip RK3572 specifications and ArmSoM’s planned Raspberry Pi Zero-form-factor product, with clear limits on power figures and board compatibility.
RKNN-Toolkit2 Python API V2.5.0 — Runtime, operator registration and inference
RKNN-Toolkit2 Python API V2.5.0 — Runtime, operator registration and inference | Complete parameters, examples and platform constraints
RKNN-Toolkit2 Python API V2.5.0 — Requirements and object lifecycle
RKNN-Toolkit2 Python API V2.5.0 — Requirements and object lifecycle | Complete parameters, examples and platform constraints
RKNN-Toolkit2 Python API V2.5.0 — Loading Caffe, TensorFlow, ONNX and PyTorch
RKNN-Toolkit2 Python API V2.5.0 — Loading Caffe, TensorFlow, ONNX and PyTorch | Complete parameters, examples and platform constraints
RKNN-Toolkit2 Python API V2.5.0 — Accuracy, performance, memory and device queries
RKNN-Toolkit2 Python API V2.5.0 — Accuracy, performance, memory and device queries | Complete parameters, examples and platform constraints
RKNN-Toolkit2 Python API V2.5.0 — Generating, building and running C++ deployment examples
RKNN-Toolkit2 Python API V2.5.0 — Generating, building and running C++ deployment examples | Complete parameters, examples and platform constraints
RKNN-Toolkit2 Python API V2.5.0 — Model configuration and quantization parameters
RKNN-Toolkit2 Python API V2.5.0 — Model configuration and quantization parameters | Complete parameters, examples and platform constraints
RKNN-Toolkit2 Python API V2.5.0 — Building, hybrid quantization and export
RKNN-Toolkit2 Python API V2.5.0 — Building, hybrid quantization and export | Complete parameters, examples and platform constraints
RKNN2 V2.5.0 quickstart 5: YOLOv5 detection and accuracy evaluation
RKNN2 V2.5.0 quickstart 5: YOLOv5 detection and accuracy evaluation · RKNN2 V2.5.0