root@davinci-mini:/home/tw/test# python3 seg.py

[INFO] acl init success 

[INFO] open device 0 success 

EE1001: The argument is invalid.Reason: ModelCheckCompatibility failed, supported socVerion=Ascend310B1, but the model socVerion=Ascend310B1 

        Solution: 1.Check the input parameter range of the function. 2.Check the function invocation relationship. 

        TraceBack (most recent call last): 

        rtModelCheckCompatibility execute failed, reason=[soc version error][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:50] 

        Call rtModelCheckCompatibility(model_soc_version.c_str(), model_arch_type.c_str()) fail, ret: 0x7BC80[FUNC:CheckModelCompatibility][FILE:om_file_helper.cc][LINE:258] 

        Check model compatibility failed.[FUNC:LoadModelData][FILE:model_helper.cc][LINE:1110] 

        [Model][FromData]load model from data failed, ge result[545002][FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161] 

[ERROR] load model from file failed, model file is 8-25.om 

[WARN] Check failed:processModel->LoadModelFromFile(modelPath), ret:1 

[WARN] no model had been loaded, unload failed 

Traceback (most recent call last): 

  File "/home/tw/test/seg.py", line 329, in <module> 

    model = YOLOv8Seg(model_path) 

  File "/home/tw/test/seg.py", line 30, in __init__ 

    self.model = InferSession(0, model_path) 

  File "/usr/local/lib/python3.10/dist-packages/ais_bench/infer/interface.py", line 62, in __init__ 

    self.session = aclruntime.InferenceSession(self.model_path, self.device_id, self.options) 

RuntimeError: [1][ACL: invalid parameter]  

[INFO] end to reset device 0 

[INFO] end to finalize acl 

---------------------------------------------------------------------------------------------------------------------

芯片为：昇腾Atlas 200i A2加速模块

CANN版本为：Ascend-cann-toolkit_7.0.RC1_linux-aarch64

在使用onnx转换后的om进行推理时遇到如上问题，一直无法解决，希望得到一些帮助！！！