rv1126 移植yolov8 pose

[AI-LLM2]

目前在移植yolov8 pose进入rv1126。转换的模型用python代码测试过是正常的。用c++代码推理结果整体score偏低只有0.1，框和关键点的位置也不对。我查了一下rk3588和rv1126的模型，发现输出的顺序反过来了。请问沿用3558 pose的代码修改后处理要怎么修改。rk3588的代码参考的是：https://github.com/cqu20160901/yolov8pose_rknn_Cplusplus

[zen-xingle]

可以参考这个https://github.com/airockchip/rknn_model_zoo/tree/main/examples/yolov8_pose，研发给的信息是下个版本会加上 rv1126/rv1109/rk1808 的支持

[fengyurenpingsheng]

可以参考这个https://github.com/airockchip/rknn_model_zoo/tree/main/examples/yolov8_pose，研发给的信息是下个版本会加上 rv1126/rv1109/rk1808 的支持

W rknn-toolkit version: 1.7.5 --> Config model done --> Loading model W Catch exception when optimize onnx model, skip it! Exception: Unresolved value references: /model.10/Constant_1_output_0,/model.10/Constant_output_0,/model.13/Constant_1_output_0,/model.13/Constant_output_0,/model.22/Constant_17_output_0,/model.22/Constant_18_output_0,/model.22/Constant_19_output_0,/model.22/Constant_1_output_0,/model.22/Constant_20_output_0,/model.22/Constant_21_output_0,/model.22/Constant_22_output_0,/model.22/Constant_23_output_0,/model.22/Constant_24_output_0,/model.22/Constant_25_output_0,/model.22/Constant_26_output_0,/model.22/Constant_27_output_0,/model.22/Constant_28_output_0,/model.22/Constant_2_output_0,/model.22/Constant_output_0, /localhome/hfa23/anaconda3/envs/rknn/lib/python3.8/site-packages/rknn/api/rknn.py:160: FutureWarning: Possible nested set at position 7 ret = self.rknn_base.load_onnx(model, inputs, input_size_list, outputs) done --> Building model Traceback (most recent call last): File "convert.py", line 60, in ret = rknn.build(do_quantization=do_quant, dataset=DATASET_PATH, auto_hybrid_quant=True) TypeError: build() got an unexpected keyword argument 'auto_hybrid_quant'

我这个会报错,知道有什么解决方案没