if__name__=='__main__':# Create RKNN object#rknn = RKNN(verbose=True)rknn=RKNN()# pre-process config,target_platform='rk3588'print('--> Config model')rknn.config(mean_values=[[0,0,0]],std_values=[[255,255,255]],target_platform='rk3588')print('done')# Load ONNX modelprint...
deep-learningnpuppyoloerk3588rk3568rk3566orange-pi-5rknpu2rock-5radxa-zero-3wradxa-zero-3-npurock5c UpdatedJun 19, 2024 C++ Paddle YOLO set: YOLOv3, PPYOLO, PPYOLOE, YOLOX, YOLOv5, YOLOv7 and so on. yolomulti-object-trackingtracking-by-detectionyolov3yolov5ppyoloyoloxbytetrackppyolov2...
cd python python convert.py <onnx_model> <TARGET_PLATFORM> <dtype(optional)> # such as: python convert.py ../model/ppyoloe_s.onnx rk3588 # output model will be saved as ../model/ppyoloe.rknn Description: <onnx_model>: Specify ONNX model path. <TARGET_PLATFORM>: Specify NPU ...