使用MDC610host-image： 1.1.026-T0000000

硬件平台： 华为MDC510     CANN 7.0  Ascend310M1onnx 以及转换到om格式时均没有使用动态格式，只使用了单条数据用于格式转换。python 代码与 onnx-runtime 均能正常运行加法代码：    def message(self,                q_i: torch.Tensor,                k_j: torch.Tensor,                v_j: torch.Tensor,                r: Optional[torch.Tensor],                index: torch.Tensor,                ptr: Optional[torch.Tensor]) -> torch.Tensor:        if self.has_pos_emb and r is not None:            k_j = k_j + self.to_k_r(r).view(-1, self.num_heads, self.head_dim) # <====== 此处加法            v_j = v_j + self.to_v_r(r).view(-1, self.num_heads, self.head_dim) # <====== 此处加法        sim = (q_i * k_j).sum(dim=-1) * self.scale        attn = softmax(sim, dim=0)        attn = self.attn_drop(attn)        return v_j * attn.unsqueeze(-1)其中 k_j 与 k_r 的形状一致，v_j 与 v_r 的形状一致 乘法代码对应以下代码中的乘法：def angle_between_2d_vectors(        ctr_vector: torch.Tensor,        nbr_vector: torch.Tensor) -> torch.Tensor:    return custom_atan2(ctr_vector[..., 0] * nbr_vector[..., 1] - ctr_vector[..., 1] * nbr_vector[..., 0],                       (ctr_vector[..., :2] * nbr_vector[..., :2]).sum(dim=-1)) 通过debug确定了在python代码中不存在维度错误，且python代码与 onnx runtime 均能正常运行报错信息：root@acf7cc422d9d:/data# atc --log=debug --model=./batch_agent_encoder_modified.onnx --framework=5 --output=./batch_agent_encoder_modify --soc_version=Ascend310M1 --input_shape="input_x_pl:86,50,128;input_data_agent_valid_mask:39,110;input_data_agent_type:39;input_data_agent_position:39,110,3;input_data_agent_heading:39,110;input_data_agent_velocity:39,110,3;input_data_map_polygon_position:86,3;input_data_map_polygon_orientation:86;input_data_agent_batch:39;input_data_map_polygon_batch:86;input_data_num_graphs:1"ATC start working now, please wait for a moment....ATC run failed, Please check the detail log, Try 'atc --help' for more informationE40021: Failed to compile Op [/t_attn_layers.0/Add]. (oppath: [Pre-compile /usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/add.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/mdc/atc/python/site-packages/tbe/dsl/classifier/broadcast_classifier.py", line 188, in classify    return [classified_ins[-1]]IndexError: list index out of range], optype: [Add])        Solution: See the host log for details, and then check the Python stack where the error log is reported.        TraceBack (most recent call last):        Pre-compile op[/t_attn_layers.0/Add] failed, oppath[/usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/add.py], optype[Add], taskID[618]. Please check op's compilation error message.[FUNC:ReportBuildErrMessage][FILE:fusion_op.cc][LINE:882]        Failed to compile Op [/Mul_10]. (oppath: [Pre-compile /usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/mul.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/mdc/atc/python/site-packages/tbe/dsl/classifier/broadcast_classifier.py", line 188, in classify    return [classified_ins[-1]]IndexError: list index out of range], optype: [Mul])        Pre-compile op[/Mul_10] failed, oppath[/usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/mul.py], optype[Mul], taskID[625]. Please check op's compilation error message.[FUNC:ReportBuildErrMessage][FILE:fusion_op.cc][LINE:882]        [SubGraphOpt][Pre-Comp][Node /t_attn_layers.0/Add] Failed to pre-compile. Tid is [133010372425472], TaskId is [618] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133010372425472].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank19_new_sub_graph103][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank19_new_sub_graph103[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /Mul_11] Failed to pre-compile. Tid is [133011060266752], TaskId is [626] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp][Node /Mul_10] Failed to pre-compile. Tid is [133011060266752], TaskId is [625] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133011060266752].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank22_new_sub_graph106][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank22_new_sub_graph106[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /t_attn_layers.0/Add_1] Failed to pre-compile. Tid is [133011085444864], TaskId is [696][FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133011085444864].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank26_new_sub_graph110][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank26_new_sub_graph110[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        Failed to compile Op [/Mul_71]. (oppath: [Pre-compile /usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/mul.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/mdc/atc/python/site-packages/tbe/dsl/classifier/broadcast_classifier.py", line 188, in classify    return [classified_ins[-1]]IndexError: list index out of range], optype: [Mul])        Pre-compile op[/Mul_71] failed, oppath[/usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/mul.py], optype[Mul], taskID[777]. Please check op's compilation error message.[FUNC:ReportBuildErrMessage][FILE:fusion_op.cc][LINE:882]        [SubGraphOpt][Pre-Comp][Node /Mul_72] Failed to pre-compile. Tid is [133011068659456], TaskId is [778] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp][Node /Mul_71] Failed to pre-compile. Tid is [133011068659456], TaskId is [777] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133011068659456].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank63_new_sub_graph241][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank63_new_sub_graph241[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        Failed to compile Op [/Mul_67]. (oppath: [Pre-compile /usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/mul.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/mdc/atc/python/site-packages/tbe/dsl/classifier/broadcast_classifier.py", line 188, in classify    return [classified_ins[-1]]IndexError: list index out of range], optype: [Mul])        Pre-compile op[/Mul_67] failed, oppath[/usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/mul.py], optype[Mul], taskID[817]. Please check op's compilation error message.[FUNC:ReportBuildErrMessage][FILE:fusion_op.cc][LINE:882]        [SubGraphOpt][Pre-Comp][Node /Mul_68] Failed to pre-compile. Tid is [133010372425472], TaskId is [818] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp][Node /Mul_67] Failed to pre-compile. Tid is [133010372425472], TaskId is [817] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank76_new_sub_graph327][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank76_new_sub_graph327[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        Failed to compile Op [/pl2a_attn_layers.1/Add]. (oppath: [Pre-compile /usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/add.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/mdc/atc/python/site-packages/tbe/dsl/classifier/broadcast_classifier.py", line 188, in classify    return [classified_ins[-1]]IndexError: list index out of range], optype: [Add])        Pre-compile op[/pl2a_attn_layers.1/Add] failed, oppath[/usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/add.py], optype[Add], taskID[827]. Please check op's compilation error message.[FUNC:ReportBuildErrMessage][FILE:fusion_op.cc][LINE:882]        [SubGraphOpt][Pre-Comp][Node /pl2a_attn_layers.1/Add] Failed to pre-compile. Tid is [133010506643200], TaskId is [827] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133010506643200].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank79_new_sub_graph330][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        [SubGraphOpt][Pre-Comp][Node /pl2a_attn_layers.0/Add] Failed to pre-compile. Tid is [133010372425472], TaskId is [927] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank79_new_sub_graph330[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank83_new_sub_graph334][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank83_new_sub_graph334[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /pl2a_attn_layers.1/Add_1] Failed to pre-compile. Tid is [133011068659456], TaskId is [884] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank81_new_sub_graph332][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank81_new_sub_graph332[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /pl2a_attn_layers.0/Add_1] Failed to pre-compile. Tid is [133010456286976], TaskId is [936] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133010456286976].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank85_new_sub_graph336][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank85_new_sub_graph336[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /t_attn_layers.1/Add_1] Failed to pre-compile. Tid is [133010498250496], TaskId is [1096] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133010498250496].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank156_new_sub_graph452][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank156_new_sub_graph452[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /t_attn_layers.1/Add] Failed to pre-compile. Tid is [133010498250496], TaskId is [1099] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank158_new_sub_graph455][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank158_new_sub_graph455[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        Failed to compile Op [/a2a_attn_layers.0/Add_1]. (oppath: [Pre-compile /usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/add.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/mdc/atc/python/site-packages/tbe/dsl/classifier/broadcast_classifier.py", line 188, in classify    return [classified_ins[-1]]IndexError: list index out of range], optype: [Add])        Pre-compile op[/a2a_attn_layers.0/Add_1] failed, oppath[/usr/local/Ascend/ascend-toolkit/mdc/x86_64-linux/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/add.py], optype[Add], taskID[963]. Please check op's compilation error message.[FUNC:ReportBuildErrMessage][FILE:fusion_op.cc][LINE:882]        [SubGraphOpt][Pre-Comp][Node /a2a_attn_layers.1/Add_1] Failed to pre-compile. Tid is [133011077052160], TaskId is [1238] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp][Node /a2a_attn_layers.0/Add_1] Failed to pre-compile. Tid is [133010456286976], TaskId is [963] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to process failed task. Thread_id is [133011077052160].[FUNC:ParallelPreCompileOp][FILE:tbe_op_store_adapter.cc][LINE:520]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank216_new_sub_graph586][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank216_new_sub_graph586[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank117_new_sub_graph409][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank117_new_sub_graph409[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /a2a_attn_layers.0/Add] Failed to pre-compile. Tid is [133011068659456], TaskId is [1019] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank121_new_sub_graph413][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank121_new_sub_graph413[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        [SubGraphOpt][Pre-Comp][Node /a2a_attn_layers.1/Add] Failed to pre-compile. Tid is [133011085444864], TaskId is [1241] [FUNC:ProcessFailPreCompTask][FILE:tbe_op_store_adapter.cc][LINE:179]        [SubGraphOpt][Pre-Comp]Failed to pre-compile graph [partition6_rank218_new_sub_graph589][FUNC:PreCompileOp][FILE:op_compiler.cc][LINE:724]        Call OptimizeFusedGraph failed, ret:-1, engine_name:AIcoreEngine, graph_name:partition6_rank218_new_sub_graph589[FUNC:OptimizeSubGraph][FILE:graph_optimize.cc][LINE:129]        subgraph 264 optimize failed[FUNC:OptimizeSubGraphWithMultiThreads][FILE:graph_manager.cc][LINE:962]        build graph failed, graph id:0, ret:-1[FUNC:BuildModel][FILE:ge_generator.cc][LINE:1505]root@acf7cc422d9d:/data#

当前设备为MDC510pro，对应CANN为 7.10.t0.0.b370，soc version为 Ascend310M1。使用atc工具将onnx转om时会报各种关于Tensor维度的错误。转换格式时指定固定维度或者动态维度都会出现不同的维度错误。例如：[INFO] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.275 [stream.cc:195] 41 DeAllocStreamSqCq: [SqCqManage]end to release sq, sq is also reuse, sq_id=0, cq_id=0, stream_id=66, is_sq_need_release=0, drv_flag=0x1.[DEBUG] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.276 [stream.cc:449] 41 DelStreamIdToStream: streamId=66.[DEBUG] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.288 [callback.cc:38] 41 Notify: stub device is no need callback.[INFO] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.291 [stream.cc:618] 41 FreeStreamId: free stream_id=64,[DEBUG] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.293 [stream.cc:157] 41 DeAllocStreamSqCq: streamIdToSqIdMap remove:stream_id=64, sq_id=0, cq_id=0.[INFO] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.294 [stream.cc:192] 41 DeAllocStreamSqCq: [SqCqManage]success to release sq, sq_id=0, cq_id=0, stream_id=64, is_sq_need_release=1, drvFlag=0.[DEBUG] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.296 [stream.cc:449] 41 DelStreamIdToStream: streamId=64.[INFO] RUNTIME(41,atc.bin):2025-10-27-17:47:56.232.303 [device.cc:94] 41 ~Device: deconstruct device[ERROR] GE(41,atc.bin):2025-10-27-17:47:56.232.307 [graph_manager.cc:1227]41 StartForRunGraph: ErrorNo: 1343242270(Prepare Graph infershape failed) [COMP][PRE_OPT][Call][PreRun] Failed, graph_id:0, session_id:0.[ERROR] GE(41,atc.bin):2025-10-27-17:47:56.232.309 [graph_manager.cc:1668]41 BuildGraph: ErrorNo: 1343242270(Prepare Graph infershape failed) [COMP][PRE_OPT][Call][StartForRunGraph] failed! graph_id:0.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.316 [error_manager.cc:254]41 ReportInterErrMessage:report error_message, error_code:E19999, work_stream_id:4100041[ERROR] GE(41,atc.bin):2025-10-27-17:47:56.232.333 [ge_generator.cc:1506]41 BuildModel: ErrorNo: 1343266819(Graph manager build graph failed.) [COMP][DEFAULT][Build][Graph] fail, graph id: 0[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.342 [graph_var_manager.cc:757]41 Destory:VarManager::Destory, session id = 0.[ERROR] GE(41,atc.bin):2025-10-27-17:47:56.232.493 [ge_generator.cc:677]41 GenerateModel: ErrorNo: 1343242270(Prepare Graph infershape failed) [COMP][DEFAULT][Build][Model] failed, ret:1343242270.[WARNING] GE(41,atc.bin):2025-10-27-17:47:56.232.616 [analyzer.cc:143]41 DestroyGraphJsonObject:can not find the stored object by session_id[0].Do nothing[ERROR] GE(41,atc.bin):2025-10-27-17:47:56.232.773 [main_impl.cc:1238]41 GenerateModel: ErrorNo: 4294967295(failed) [COMP][DEFAULT]GE GenerateOfflineModel execute failed[ERROR] GE(41,atc.bin):2025-10-27-17:47:56.232.779 [main_impl.cc:1239]41 GenerateModel: ErrorNo: 4294967295(failed) [COMP][DEFAULT]ATC Generate execute failed[WARNING] GE(41,atc.bin):2025-10-27-17:47:56.232.782 [graph_manager.cc:439]41 Finalize:GraphManager has not been initialized.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.785 [gelib.cc:473]41 Finalize:finalization start[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.787 [gelib.cc:484]41 Finalize:engineManager finalization.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.789 [dnnengine_manager.cc:180]41 Finalize:DNNEngine name: AIcoreEngine.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.790 [dnnengine_manager.cc:180]41 Finalize:DNNEngine name: DNN_HCCL.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.792 [dnnengine_manager.cc:180]41 Finalize:DNNEngine name: DNN_VM_AICPU.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.232.793 [dnnengine_manager.cc:180]41 Finalize:DNNEngine name: DNN_VM_AICPU_ASCEND.和[INFO] GE(41,atc.bin):2025-10-27-17:47:56.936.942 [process_node_engine_manager.cc:87]41 Finalize:ProcessNodeEngine id:UDF.[DEBUG] GE(41,atc.bin):2025-10-27-17:47:56.937.254 [node_compile_cache_module.cc:443]41 Finalize:Finalize ccm.[INFO] GE(41,atc.bin):2025-10-27-17:47:56.937.267 [gelib.cc:548]41 Finalize:finalization success.[WARNING] GE(41,atc.bin):2025-10-27-17:47:56.937.433 [graph_manager.cc:439]41 Finalize:GraphManager has not been initialized....[WARNING] GE(41,atc.bin):2025-10-27-17:47:56.945.576 [main_impl.cc:1566]41 CheckRet:ATC generate offline model failed.ATC run failed, Please check the detail log, Try 'atc --help' for more information[INFO] GE(41,atc.bin):2025-10-27-17:47:56.945.586 [error_manager.cc:376]41 GetErrorMessage:current work_stream_id:4100041E89999: Inner Error!E89999  op[/Concat_19], the input shape dims should be equal except merge axis,shapes:[[0, 1, ], [1, 1, ], ]axis:-1[FUNC:ConcatInferShapeCommon][FILE:split_combination_ops.cc][LINE:892]        TraceBack (most recent call last):        Call InferShapeAndType for node:/Concat_19(ConcatD) failed[FUNC:Infer][FILE:infershape_pass.cc][LINE:119]        process pass InferShapePass on node:/Concat_19 failed, ret:4294967295[FUNC:RunPassesOnNode][FILE:base_pass.cc][LINE:571]        build graph failed, graph id:0, ret:1343242270[FUNC:BuildModel][FILE:ge_generator.cc][LINE:1505][INFO] GE(41,atc.bin):2025-10-27-17:47:56.946.172 [main_impl.cc:1637]41 GetMemInfo:Find mem [MemAvailable] info line [MemAvailable:   12196748 kB][INFO] GE(41,atc.bin):2025-10-27-17:47:56.946.186 [main_impl.cc:1645]41 GetMemInfo:Find mem [MemAvailable] info [12196748 kB]. 但原有的python代码运行正常且不存在维度错误。使用 onnx-runtime 加载 onnx 模型也可以正常运行。尝试通过升级CANN软件版本解决问题。从官网下载社区版 CANN8.1，其不支持当前 soc_version。当指定 soc_version 参数为 Ascend310P3或Ascend610 时，可以成功将当前onnx转为om格式。现有疑问：MDC510pro 的 atc 工具在格式转换时的维度错误该如何解决？能否通过升级软件版本解决问题？如何获取支持当前 soc_version（Ascend310M1） 的 CANN toolkit？

修改网络配置后，将B3口的速率改为100后，也通过校验。然后重启的时候就报错，错误如下：MDC reset: ERROR: MDC Reset failed! StateTransition Arbitration failed  这个怎么解决

1.产品名称：MDC6102.软件版本：MDC610 1.1.027-T000  MDC_Manifest_Configurator-2.2.001-0000000-Ubuntu20  MDC_Development_Studio-2.2.001-0000000-Ubuntu20相机为森云的可见光相机基于MMC搭建的节点通讯框架如下3.问题描述：在MDS中自动生成代码后，我们想测试MDC能否正常接收到相机的图像数据，并打印出一帧yuv图像或原始数据，请问应该如何操作？4.已采取的措施：在sample.cpp中编写了如下代码，希望获取到data（类型为CameraDecodedMbufStruct消息结构体）中的Rawdata，Rawdata在文档中的描述为图像数据#include "mdc/sample.h"#include <chrono>#include <functional>namespace mdc {Sample::Sample(): swcPtr_(std::make_unique<mdc::camera_det_base::CameraDetBaseSwC>()), workFlag_(true){}Sample::~Sample(){    if (workFlag_) {        Stop();    }}bool Sample::InitHandle(){    SPL_LOG_SPACE::GetLoggerIns("SPL")->LogInfo()<< "Some operations during initialization.";    return true;}void Sample::StopHandle(){    SPL_LOG_SPACE::GetLoggerIns("SPL")->LogInfo()<< "Some operations during stopping";    return;}bool Sample::Init(){    SPL_LOG_SPACE::InitAppLogging();    SPL_LOG_SPACE::InitLoggerCtx("SPL", "sample log contex");    if (!swcPtr_) {        SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "Failed to create the SWC object.";        return false;    }    swcPtr_->SetInitCallback(std::bind(&Sample::InitHandle));    swcPtr_->SetStopCallback(std::bind(&Sample::StopHandle));    if (!swcPtr_->Init()) {        SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "SWC initialization failed.";        return false;    }    return true;}void Sample::Run(){    Object2dArrayIntfServerThreadPtr_ =        std::make_unique<std::thread>(std::bind(&Sample::Object2dArrayIntfServerRun, this));    CameraDecodedMbufServiceInterfaceClientThreadPtr_ =        std::make_unique<std::thread>(std::bind(&Sample::CameraDecodedMbufServiceInterfaceClientRun, this));}void Sample::Object2dArrayIntfServerRun(){    if (!swcPtr_) {        SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "The swc object is empty.";        return;    }    /* 获取本应用所有的发送端口，获取到的端口名对应MMC上本应用配置的发送端口名 */    auto object2dArrayIntfServerPortVec = swcPtr_->GetObject2dArrayIntfServerVec();    while (workFlag_) {        /* 遍历port name，获取服务端对象并发送数据 */        for (const auto& portName : object2dArrayIntfServerPortVec) {            if (!workFlag_) {                return;            }            /* 获取发送端服务，其中portName对应MMC上配置的此应用对应的发送端portName <关键接口> */            auto serverPtr = swcPtr_->GetObject2dArrayIntfServer(portName);            if (!serverPtr) {                SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "Failed to initialize the instance: " << portName;                continue;            }            auto data = std::make_shared<adsfi::Object2dArrayDataType>();            /* Event事件，发送数据，非阻塞接口 <关键接口> */            serverPtr->SendObject2dArrayData(data);            std::this_thread::sleep_for(std::chrono::milliseconds(500U));        }    }}void Sample::CameraDecodedMbufServiceInterfaceClientRun(){    if (!swcPtr_) {        SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "The swc object is empty.";        return;    }    /* 获取本应用所有的接收端口，获取到的端口名对应MMC上本应用配置的接收端口名 */    auto cameraDecodedMbufServiceInterfaceClientPortVec = swcPtr_->GetCameraDecodedMbufServiceInterfaceClientVec();    while (workFlag_) {        /* 遍历port name，获取客户端对象并注册接收到数据后的回调函数 */        for (const auto& portName : cameraDecodedMbufServiceInterfaceClientPortVec) {            if (!workFlag_) {                return;            }            /* 获取接收端服务，其中portName对应MMC上配置的此应用对应的接收端portName <关键接口> */            auto clientPtr = swcPtr_->GetCameraDecodedMbufServiceInterfaceClient(portName);            if (!clientPtr) {                SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "Failed to initialize the instance: " << portName;                continue;            }            /* Event事件，注册接收到数据后的回调函数 */            clientPtr->RegisterCameraDecodedMbufEventNotifyHandler(                std::bind(&Sample::ReceiveMdcCamCameraCameraDecodedMbufEventDataHandle,                std::placeholders::_1));            /* 获取数据，非阻塞方式 <关键接口> */            auto oneData = clientPtr->GetCameraDecodedMbufEventOneData();            /* 获取数据，一次获取5个数据，非阻塞方式 <关键接口> */            auto nData = clientPtr->GetCameraDecodedMbufEventNdata(5U);            /* 获取数据，阻塞式接口，超时时间为1000ms <关键接口> */            auto oneDataBlocking = clientPtr->GetCameraDecodedMbufEventOneDataBlocking(1000U);        }    }}void Sample::Stop(){    workFlag_ = false;    if ((Object2dArrayIntfServerThreadPtr_ != nullptr) &&        (Object2dArrayIntfServerThreadPtr_->joinable())) {        Object2dArrayIntfServerThreadPtr_->join();    }    Object2dArrayIntfServerThreadPtr_ = nullptr;    if ((CameraDecodedMbufServiceInterfaceClientThreadPtr_ != nullptr) &&        (CameraDecodedMbufServiceInterfaceClientThreadPtr_->joinable())) {        CameraDecodedMbufServiceInterfaceClientThreadPtr_->join();    }    CameraDecodedMbufServiceInterfaceClientThreadPtr_ = nullptr;    SPL_LOG_SPACE::GetLoggerIns("SPL")->LogInfo()<< "Thread resources reclaimed successfully..";    if (!swcPtr_) {        SPL_LOG_SPACE::GetLoggerIns("SPL")->LogError()<< "The swc object is empty.";        return;    }    swcPtr_->Stop();}void Sample::ReceiveMdcCamCameraCameraDecodedMbufEventDataHandle(const mdc::cam::camera::cameraDecodedMbufEventDataType& data){    const ara::camera::CameraDecodedMbufStruct& mbufData =        static_cast<const ara::camera::CameraDecodedMbufStruct&>(data);    // 调用GetMbufPtr()方法获取缓冲区指针    ::rawBuffer* mbufPtr = mbufData.GetMbufPtr();    // 输出日志信息，包括缓冲区指针和关键属性    SPL_LOG_SPACE::GetLoggerIns("SPL")->LogInfo()        << "Received camera decoded mbuf data - "        << "Width: " << mbufData.Width << ", "        << "Height: " << mbufData.Height << ", "        << "DataSize: " << mbufData.DataSize << ", "        << "FrameType: " << mbufData.FrameType << ", "        << "MbufPtr: " << static_cast<void*>(mbufPtr);}}打包在mdc上运行，打印出的部分日志如下：2025/01/21 18:21:31.702187358 2025/01/21 18:21:31.702175665 018 A102 CLNT info [cameraDecodedMbufEvent: data received. instanceId: 21]2025/01/21 18:21:31.735434024 2025/01/21 18:21:31.735423373 006 A102 SPL info [Received camera decoded mbuf data - Width: 1920, Height: 1080, DataSize: 4147200, FrameType: 1004, MbufPtr: 3fa]2025/01/21 18:21:31.735484233 2025/01/21 18:21:31.735472800 022 A102 CLNT info [cameraDecodedMbufEvent: data received. instanceId: 21]2025/01/21 18:21:31.768783347 2025/01/21 18:21:31.768773087 007 A102 SPL info [Received camera decoded mbuf data - Width: 1920, Height: 1080, DataSize: 4147200, FrameType: 1004, MbufPtr: 3f9]可以看出Mbuf的值过低，不是有效地址，并不直接指向图像原始数据。也没有找到其他指向图像数据的接口。

产品名称：MDC610软件版本：MDC 610 1.1.027-T000问题现象：在MBD打包运行后客户端接收不到数据日志打印部分报错内容如下：2024/09/06 20:41:21.816586693 2024/09/06 20:41:21.816575911 003 ____ EM warn [11867-11867 [RpcClient][EM operating environment is nullptr, use default value][isolate_communication=false]]2024/09/06 20:41:21.820795078 2024/09/06 20:41:21.820784844 005 ____ EM warn [11867-11867 [ExecutionClientInner][EM dlopen failed][dlopen_error=libexec_client_extension.so: cannot open shared object file: No such file or directory]][11867-11882 [DDSEventHandler][Reader enable error, delete reader][serviceId=2434, instanceId=21, entityId=3920, topicName=CameraDecodedDdsEvent, retCode=ERROR]]故障后采取的措施：在导出配置过程中，需要进行PingTool，完成ADSFI通信链路诊断的场景化校验。但在PingTool此工程后，一般会遇到报错问题如下图所示。报错内容如下：The Process is not associated with a ProcessToMachineMapping.[mdc_constr_2006] Each Process shall be mapped by a ProcessToMachineMapping to one Machine.The value of ServiceInterface corresponding to the Executable associated with ServiceInstanceToPortPrototypeMapping('CameraDecodedMbufPPort_DdsProvidedServiceInstance1_PortMapping') must be the same as the value of ServiceInterface corresponding to the ServiceInstance referenced by ServiceInstanceToPortPrototypeMapping('CameraDecodedMbufPPort_DdsProvidedServiceInstance1_PortMapping').The value of ServiceInterface corresponding to the Executable associated with ServiceInstanceToPortPrototypeMapping('RPortPrototype1_DdsRequiredServiceInstance1_PortMapping') must be the same as the value of ServiceInterface corresponding to the ServiceInstance referenced by ServiceInstanceToPortPrototypeMapping('RPortPrototype1_DdsRequiredServiceInstance1_PortMapping').我的解决方法1.2.操作之后显示 The communication of CM is normal.虚拟传感器源端口属性配置如下这里手册给的案例图片内QoS Profile的取值为default.xml，但我查找了MDC610的产品档案，要求配置客户端应用ARXML时，需确保QoS的关键配置项和服务端ARXML一致，我查看了default.arxml中的服务端的通信配置，并以此配置端口属性。我的报错原因分析：是否是Reader创建失败导致无法监听CameraDecodedDdsEvent话题，即使服务端发布数据，客户端也无法获取数据样本，从而导致接收数据为空。服务端是否正常发布数据。日志全文放在附件

产品名称：MDC 610软件版本：MDC 610 1.99.202-0000000     问题现象（问题描述）：在上位机环境中编译好的可执行文件，scp传输到MDC610的/opt/usr/路径下，运行的时候总是报"Permission denied"，但是运行前已经给可执行文件添加了执行权限。放到/opt/platform/mdc_platform/bin/路径下却能正常运行，请问是什么原因呢？

最近把MDC610的软件版本从1.1.027升级到了1.99.202，发现1.1.027提供的传感器抽象服务到1.99.202版本都没有了，给软件开发和代码移植带来了很多困难，不太理解为什么要这样做。请问MDC610开发者是基于什么考虑不再提供传感器抽象呢？1.1.027提供的抽象服务可以拷贝到1.99.202上直接用吗？

产品名称：MDC 510软件版本：MDC 510 1.0.005-T0000020.SPC1问题现象（问题描述）：将 onnx 格式模型转为om格式时 NonZero 算子不支持。标准的 CANN好像支持这个算子，但是mdc510开发环境中不支持这个算子故障后已采取的措施：尝试修改模型，但多次尝试未能绕过 NonZero 算子。自定义 NonZero 算子未成功示例代码（如有）：涉及 indexslice 的操作。使用Tensor作为索引进行切片操作时生成NonZero算子。例如：        edge_index_t = edge_index_t[:, edge_index_t[1] > edge_index_t[0]]        edge_index_t = edge_index_t[:, edge_index_t[1] - edge_index_t[0] <= self.time_span]    col, row = torch.where(bool_dist)        edge_index_pl2a = edge_index_pl2a[:, mask_s[edge_index_pl2a[1]]]    edge_index = edge_index[:, edge_mask]onnx转换为om格式时的命令与报错：root@acf7cc422d9d:/data# atc --model=./model_batch_11.onnx --framework=5 --output=./model_batch_11 --soc_version=Ascend310M1ATC start working now, please wait for a moment....ATC run failed, Please check the detail log, Try 'atc --help' for more informationE19010: No parser is registered for Op [/agent_encoder/NonZero, optype [ai.onnx::11::NonZero]].        Solution: Check the version of the installation package and reinstall the package. For details, see the operator specifications.        TraceBack (most recent call last):        No parser is registered for Op [/agent_encoder/NonZero_1, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_2, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_3, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_4, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_5, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_6, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_7, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/agent_encoder/NonZero_8, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_1, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_2, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_3, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_4, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_5, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_6, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_7, optype [ai.onnx::11::NonZero]].        No parser is registered for Op [/decoder/NonZero_8, optype [ai.onnx::11::NonZero]].        Model parse to graph failed, graph name:model_batch_11.[FUNC:ModelParseToGraph][FILE:onnx_parser.cc][LINE:925]        ATC model parse ret fail.[FUNC:ParseGraph][FILE:omg.cc][LINE:792]root@acf7cc422d9d:/data#

产品名称：MDC 610软件版本：MDC 610 1.99.202-0000000     问题现象（问题描述）：我们把相机接入了MDC，想将相机捕获的图像在Mviz中显示出来。用mdc::visual::Publisher接口发布相机数据，写代码时候有个疑问：Publisher类接口中定义了函数原型bool Publisher::Publish(const Image &iImage)作用域namespace mdc::visual参数输入Image数据返回值true：发布成功false：发布失败头文件#include“publisher.h”描述Image数据发送接口。这里Image结构体里定义的ara::core::Vector<uint8_t> frameData是RGB码流吗？另外，Image结构体为什么没有width和height字段？只发布Vector类型的码流，MViz能将图像可视化出来吗？函数原型Image(Header vHeader, ara::core::Vector<uint8_t> vFrames)作用域namespace mdc::visual参数输入vHeader：Header类型vFrames：ara::core::Vector<uint8_t>类型返回值无头文件#include "publisher.h"描述构造函数。

产品名称：MDC 610软件版本：MDC 610 1.99.202-0000000     问题现象（问题描述）：MDC 610 1.99.202版本新增了对艾瑞红外相机的适配，我们现在手头上有一台艾瑞光电Asens M6+红外相机，MDC 610的软件版本已经升级到1.99.202，想测试一下MDC能否正常接收到红外相机的图像。我们参考1.99.102版本的代码案例编写了接收相机YUV格式图像的代码，并将YUV图像保存到本地；打印出了原始数据的前100位，用于调试。代码如下：#include <cstdio> #include <fstream> #include <iostream> #include <string> #include <thread> #include <vector> #include "ara/log/logging.h" #include "camera.h" #include "camera_venc.h" #include "camera_mviz.h" #include "ascend_hal.h" using namespace mdc; using namespace mdc::camera; const std::vector<CameraAccessConfig> access = { { .moduleName = "MDC_IRAY_RTD6122C_MAX96705", .cameraId = 0U, .fov = 120U, .fps = 30, .width = 640U, .height = 512U, .streamDepth = 10U, .clusterId = 0U, }, }; void ProcessCameraData(const uint32_t cameraId, CameraData &camData) { static std::vector<uint32_t> count(16U); // 默认最多16个camera ++count[cameraId]; if ((count[cameraId] <= 100) || (count[cameraId] > 110)) { // 只保留10帧yuv return; } std::string fileNameYuv = "dump_camera" + std::to_string(cameraId) + "_" + "seq" + std::to_string(camData.seq) + ".yuv"; // 获取yuv数据 MDCMbuf mbuf; mbuf.SetMbuf(camData.yuvData); if (!mbuf.isValid()) { std::cout << "[ERROR] cameraId: " << cameraId << " get yuvdata failed\n"; return; } void *data = nullptr; uint64_t size = 0U; mbuf.GetBuffData(data, size); mbuf.GetDataLen(size); mbuf.Free(); std::cout << "cameraId " << cameraId << " seq " << camData.seq << " yuv " << data << " size " << size << ", write file : " << fileNameYuv << "\n"; if (data != nullptr && size > 0) { uint8_t* byteData = static_cast<uint8_t*>(data); uint64_t printSize = std::min<uint64_t>(size, 100ULL); std::cout << "First" << printSize << "bytes of data:\n"; for (uint64_t i = 0; i < printSize; i++) { // 以十六进制格式打印，每个字节占2位，不足位补0 std::cout << std::hex << std::setw(2) << std::setfill('0') << static_cast<int>(byteData[i]) << " "; if ((i + 1) % 16 == 0) { std::cout << "\n"; } } std::cout << std::dec << "\n"; } else { std::cout << "No valid data to print.\n"; } // 保存yuv数据 FILE *fp = fopen(fileNameYuv.c_str(), "wb"); if (fp == nullptr) { std::cout << fileNameYuv << "open failed.\n"; return; } fwrite(data, 1, size, fp); fclose(fp); return; } int32_t main(int32_t argc, char *argv[]) { ara::log::InitLogging("camera", "SENSOR ACCESS", ara::log::LogLevel::kInfo, ara::log::LogMode::kRemote | ara::log::LogMode::kConsole); //ara::log::LogMode::kRemote); constexpr int32_t timeout = 1000; // step0.mbuf系统资源初始化 MDCMbufSysInit(); // step1.初始化Camera int32_t ret = CameraInit(access); if (ret != 0) { std::cout << "[ERROR] CameraInit failed, ret = " << ret << "\n"; return -1; } int32_t count = 3000; // 测试300帧 while ((--count) > 0) { std::cout << "Waiting Events ... ..." << std::endl; std::vector<uint32_t> camIds = CameraWaitEvents(timeout); for (const auto &cam : camIds) { std::cout << "Camera event come : " << cam << "\n"; std::vector<CameraData> camDatas; int32_t ret = CameraGetData(cam, camDatas, timeout); if (ret != 0) { std::cout << "[ERROR] CameraGetData failed, ret = " << ret << "\n"; continue; } for (auto &camData : camDatas) { ProcessCameraData(cam, camData); camData.yuvData.Free(); } } } // step3.退出camera，去初始化 ret = CameraDeinit(); if (ret != 0) { std::cout << "[ERROR] CameraDeinit failed, ret = " << ret << "\n"; return -1; } // step4.mbuf系统资源反初始化 MDCMbufSysExit(); std::cout << "run camera success"<< "\n"; return 0; }在本地对YUV格式图像进行可视化时，发现图像呈现出的是一片灰色，看不到正常的热力图。查看打印出的原始数据，发现原始数据每一个字节都是0x80，推断是MDC接收到的相机原始数据是错误的。First100bytes of data: 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 80 同样的代码，接入森云的可见光相机时，修改CameraAccessConfig后，接收到的YUV图像和原始数据都是正常的。请问可能是什么原因呢？

产品名称：MDC 610 软件版本：MDC 610 1.1.027-T000在610平台上抓毫米波的包数据发现只有毫米波发出的数据信息，并没有看到ptp消息，请问这是为什么没有ptp消息？是需要毫米波设置还是配置610还是什么？急！

产品名称：MDC 610 软件版本：MDC 610 1.1.027-T000 产品文档      求助问题现象：目前MDC610已经利用组合定位传感器获取到时间，但MDC断电再次开机之后，时间会回到上次断电的时间，如何保证MDC610 断电之后时间继续运行？MDC内部是否存在断电计时源？如何设置？

产品名称：MDC 610 软件版本：MDC 610 1.1.027-T000需求：我们想要给大陆ARS548这款4D毫米波雷达同MDC610 数据面时间同步，但是这款雷达是UDP通信，所以不能通过CANTSN授时，只能通过gPTP授时，同时该4D毫米波也是支持gPTP方式时间同步。想知道如何将610同步时间信号给到ARS548完成时间同步？

在完成MMC导出配置文件后，按产品文档进行了如下操作  之后的Console视图显示 当前项目中没有组件  我做了如下检查工作1.打开MDS工具，查看工程目录“manifest/modules”中是否有相关组件的配置 2.检查MMC搭建的节点通信框架