acl.mdl.execute failed ret=507011 运行Resnet50分类代码出错
收藏回复举报
acl.mdl.execute failed ret=507011 运行Resnet50分类代码出错
t('forum.solved') 已解决
发表于2023-09-27 13:34:28
0 查看
execute stage:
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.022.583 [engine.cc:3580]234853 ProcLogicCqReport:[EXEC][DEFAULT]CQE error, device_id=0, stream_id=1, ta                      sk_id=5, sqe_type=7, errType=0x20(sq sw status error), sqSwStatus=0x10020000
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.516 [device_error_proc.cc:1091]234853 ProcessStarsCoreErrorInfo:[EXEC][DEFAULT]report error module_                      type=5, module_name=EZ9999
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.554 [device_error_proc.cc:1091]234853 ProcessStarsCoreErrorInfo:[EXEC][DEFAULT]The error from devic                      e(chipId:0, dieId:0), serial number is 19, there is an aicore error exception, core id is 0, error code = 0x10, dump info: pc start: 0xe80000027000, curren                      t: 0xe80000027040, vec error info: 0, mte error info: 0xbf037febff, ifu error info: 0xb7f7ff78bf980, ccu error info: 0x804000004e000002, cube error info: 0                      , biu error info: 0, aic error mask: 0x65000208d000288, para base: 0xe8000009be00.
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.668 [device_error_proc.cc:1103]234853 ProcessStarsCoreErrorInfo:[EXEC][DEFAULT]report error module_                      type=5, module_name=EZ9999
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.687 [device_error_proc.cc:1103]234853 ProcessStarsCoreErrorInfo:[EXEC][DEFAULT]The extend info: err                      code:(0x10, 0, 0) errorStr: Illegal instruction, which is usually caused by unaligned UUB addresses. fixp_error0 info: 0x37febff, fixp_error1 info: 0xbf fs                      mId:0, tslot:0, thread:0, ctxid:0, blk:0, sublk:0, subErrType:4.
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.793 [task_info.cc:4518]234853 ReportErrorInfoForModelExecuteTask:[EXEC][DEFAULT]model execute error                      , retCode=0x91, [the model stream execute failed].
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.815 [task_info.cc:4485]234853 PrintErrorInfoForModelExecuteTask:[EXEC][DEFAULT]stream_id=1, task_id                      =4, sq_id=2, fsm_state=0, sqVirtualAddr=3277242368, head equal tail flag=0.
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.832 [task_info.cc:4491]234853 PrintErrorInfoForModelExecuteTask:[EXEC][DEFAULT]model execute task f                      ailed, device_id=0, model stream_id=1, model task_id=4, flip_num=0, model_id=0, first_task_id=0
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.023.949 [task_info.cc:1472]234853 PrintErrorInfoForDavinciTask:[EXEC][DEFAULT]Aicore kernel execute fai                      led, device_id=0, stream_id=2, report_stream_id=1, task_id=0, flip_num=0, fault kernel_name=456876782376805633-1_0_1_data_0_huawei_aippconv1conv1_relu, pro                      gram id=0, hash=8015895112059683207.
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.000 [task_info.cc:1415]234853 GetArgsInfo:[EXEC][DEFAULT][AIC_INFO] args(0 to 12) after execute:0xe                      8000009c800, 0xe80001400400, 0xe800040d0c00, 0xe80004600200, 0xffffffffffffffff, 0, 0xffffffffffffffff, 0, 0xffffffffffffffff, 0, 0, 0,
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.025 [task_info.cc:1476]234853 PrintErrorInfoForDavinciTask:[EXEC][DEFAULT][AIC_INFO] after execute:                      args print end
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.148 [stream.cc:1461]234853 GetError:[EXEC][DEFAULT]Stream Synchronize failed, stream_id=1, retCode=                      0x91, [the model stream execute failed].
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.168 [stream.cc:1464]234853 GetError:[EXEC][DEFAULT]report error module_type=5, module_name=EZ9999
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.183 [stream.cc:1464]234853 GetError:[EXEC][DEFAULT]Aicore kernel execute failed, device_id=0, strea                      m_id=2, report_stream_id=1, task_id=0, flip_num=0, fault kernel_name=456876782376805633-1_0_1_data_0_huawei_aippconv1conv1_relu, program id=0, hash=8015895                      112059683207.
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.219 [stream.cc:1464]234853 GetError:[EXEC][DEFAULT]report error module_type=5, module_name=EZ9999
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.234 [stream.cc:1464]234853 GetError:[EXEC][DEFAULT][AIC_INFO] after execute:args print end
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.256 [model.cc:669]234853 SynchronizeExecute:[EXEC][DEFAULT]report error module_type=0, module_name=                      EE9999
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.270 [model.cc:669]234853 SynchronizeExecute:[EXEC][DEFAULT]Fail to synchronize forbbiden stream, re                      tCode=0x7150050!
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.334 [model.cc:709]234853 GetStreamToSyncExecute:[EXEC][DEFAULT]report error module_type=0, module_n                      ame=EE9999
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.348 [model.cc:709]234853 GetStreamToSyncExecute:[EXEC][DEFAULT]Model synchronize execute failed, mo                      del_id=0!
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.372 [logger.cc:1044]234853 ModelExecute:[EXEC][DEFAULT]Execute model failed.
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.401 [api_c.cc:2330]234853 rtModelExecute:[EXEC][DEFAULT]ErrCode=507011, desc=[the model stream exec                      ute failed], InnerCode=0x7150050
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.415 [error_message_manage.cc:50]234853 FuncErrorReason:[EXEC][DEFAULT]report error module_type=3, m                      odule_name=EE8888
[ERROR] RUNTIME(234853,python3):2023-09-27-21:27:27.024.434 [error_message_manage.cc:50]234853 FuncErrorReason:[EXEC][DEFAULT]rtModelExecute execute failed                      , reason=[the model stream execute failed]
[ERROR] GE(234853,python3):2023-09-27-21:27:27.024.496 [davinci_model.cc:5299]234853 NnExecute: ErrorNo: 1343225859(Failed to call runtime API!) [EXEC][DEF                      AULT]Call rt api failed, ret: 0x7BC83
[ERROR] GE(234853,python3):2023-09-27-21:27:27.024.521 [graph_loader.cc:236]234853 ExecuteModel: ErrorNo: 507011() [EXEC][DEFAULT][Execute][Model] failed,                       model_id:1.
[ERROR] ASCENDCL(234853,python3):2023-09-27-21:27:27.024.541 [model.cpp:870]234853 ModelExecute: [EXEC][DEFAULT][Exec][Model]Execute model failed, ge resul                      t[507011], modelId[1]
[ERROR] ASCENDCL(234853,python3):2023-09-27-21:27:27.024.574 [model.cpp:1767]234853 aclmdlExecute: [EXEC][DEFAULT][Exec][Model]modelId[1] execute failed, r                      esult[507011]
Traceback (most recent call last):
  File "/root/tmp/642e6624-38a1-4e78-8864-d3113aef6bfc/resnet50_imagenet_classification/src/acl_net.py", line 295, in <module>
    net.run([img])
  File "/root/tmp/642e6624-38a1-4e78-8864-d3113aef6bfc/resnet50_imagenet_classification/src/acl_net.py", line 201, in run
    self.forward()
  File "/root/tmp/642e6624-38a1-4e78-8864-d3113aef6bfc/resnet50_imagenet_classification/src/acl_net.py", line 209, in forward
    check_ret("acl.mdl.execute", ret)
  File "/root/tmp/642e6624-38a1-4e78-8864-d3113aef6bfc/resnet50_imagenet_classification/src/acl_net.py", line 31, in check_ret
    raise Exception("{} failed ret={}"
Exception: acl.mdl.execute failed ret=507011

错误代码如上 运行的实例仓为:https://gitee.com/ascend/samples/tree/master/python/level2_simple_inference/1_classification/resnet50_imagenet_classification/#env 代码、图片、模型为事例中,而环境为Atlas 200DkA2

我要发帖子