2.4K Star 8.2K Fork 4.4K

GVPMindSpore / mindspore

 / 详情

[MT][710] unet_simple模型在710机器推理的infer.log有error日志,acc.log正常

DONE
Bug-Report
创建于  
2024-05-20 15:05
name about labels
Bug Report Use this template for reporting a bug kind/bug

Describe the current behavior / 问题描述 (Mandatory / 必填)

unet_simple模型在710机器推理的infer.log有error日志,acc.log正常

Environment / 环境信息 (Mandatory / 必填)

  • Hardware Environment(Ascend/GPU/CPU) / 硬件环境:

Please delete the backend not involved / 请删除不涉及的后端:
/device Ascend

  • Software Environment / 软件环境 (Mandatory / 必填):
    -- MindSpore version (e.g., 1.7.0.Bxxx) :commit_id = '[sha1]:2f410aa8
    -- Python version (e.g., Python 3.7.5) :Python 3.7.5
    -- OS platform and distribution (e.g., Linux Ubuntu 16.04):#48-Ubuntu
    -- GCC/Compiler version (if compiled from source):gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
    run包:Milan_C18/20240517
    whl包:MindSpore/2.3.0/B521/Publish/
  • Excute Mode / 执行模式 (Mandatory / 必填)(PyNative/Graph):

Please delete the mode not involved / 请删除不涉及的模式:
/mode graph

Related testcase / 关联用例 (Mandatory / 必填)

test_ms_unet_simple_mindir_infer_0001

Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)

1.get code from solution_test
2.cd solution_test/cases/02network/00cv/unet/infer
3. pytest -s test_ms_unet_simple_mindir_infer_0001.py

Describe the expected behavior / 预期结果 (Mandatory / 必填)

unet_simple模型在710机器推理的infer.log没有error日志,acc.log正常

Related log / screenshot / 日志 / 截图 (Mandatory / 必填)

部分日志如下
INFO 2024-05-20 10:03:13 - test_ms_unet_simple_mindir_infer_0001 - base.py:check_err_info_in_log:985 - >>>>>>>>>>>>>>>>>>>> Start checking ERROR info from log <<<<<<<<<<<<<<<<<<<<
ERROR 2024-05-20 10:03:13 - test_ms_unet_simple_mindir_infer_0001 - base.py:check_err_info_in_log:988 -
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:01.856.442 [engine.cc:1514]56748 ReportExceptProc:Task exception! device_id=0, stream_id=1, task_id=1, type=97(STARS_VERSION), failuremode =0, retCode=0x97, [t ask type not support]
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:01.869.952 [stream.cc:1501]56748 GetError:Stream Synchronize failed, stream_id=1, retCode=0x97, [task type not support].
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:01.869.978 [aicpu_err_msg.cc:188]56748 SendConfigMsgToAicpu:apicpu kernel launch failed, retCode=0x7100003.
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:01.869.988 [aicpu_err_msg.cc:221]56748 SetErrMsgBufAddr:set err msg buf addr to aicpu failed, retCode=0x7100003, [task type not support].
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:57.767.069 [engine.cc:1514]56748 ReportExceptProc:Task exception! device_id=0, stream_id=1, task_id=1, type=97(STARS_VERSION), failuremode =0, retCode=0x97, [t ask type not support]
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:57.780.715 [stream.cc:1501]56748 GetError:Stream Synchronize failed, stream_id=1, retCode=0x97, [task type not support].
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:57.780.739 [aicpu_err_msg.cc:188]56748 SendConfigMsgToAicpu:apicpu kernel launch failed, retCode=0x7100003.
[ERROR] RUNTIME(56748,main):2024-05-20-10:02:57.780.760 [aicpu_err_msg.cc:221]56748 SetErrMsgBufAddr:set err msg buf addr to aicpu failed, retCode=0x7100003, [task type not support].
INFO 2024-05-20 10:03:13 - test_ms_unet_simple_mindir_infer_0001 - base.py:check_err_info_in_log:989 - >>>>>>>>>>>>>>>>>>>> Stop checking ERROR info from log <<<<<<<<<<<<<<<<<<<<
ERROR 2024-05-20 10:03:13 - test_ms_unet_simple_mindir_infer_0001 - test_ms_unet_simple_mindir_infer_0001.py:test_run:140 - Something wrong with train or infer, pls check error log.

Special notes for this issue/备注 (Optional / 选填)

unet_simple模型在710机器推理的infer.log有error日志,acc.log正常;310机器没有这个问题

评论 (5)

chentangyu 创建了Bug-Report
chentangyu 添加了
 
kind/bug
标签
chentangyu 添加了
 
attr/function
标签
chentangyu 添加了
 
device/ascend
标签
chentangyu 添加了
 
v2.3.0.rc3
标签
chentangyu 添加了
 
rct/cann
标签
chentangyu 添加协作者chentangyu
chentangyu 添加协作者wangbixing
chentangyu 负责人设置为wangbixing
chentangyu 取消协作者wangbixing
chentangyu 关联仓库设置为MindSpore/mindspore
chentangyu 里程碑B-MDTest 修改为B-SIG-TBD
展开全部操作日志

用例test_ms_resnet50_imagenet_310_mindir_infer_0001也有此问题。

Test_ms_dbnet_mobilenetv3_icdar15_lite_mindir_infer_0001
Test_ms_crnn_vgg7_data_lmdb_release_lite_mindir_infer_0001

test_ms_crnn_crnn_ds_mindir_infer_0001

chentangyu 添加了
 
master
标签
fangwenyi 添加了问题后端类型Ascend 选项
fangwenyi 添加了关联分支master 选项
wangbixing 添加了
 
br_base
标签
wangbixing 添加了
 
br_base
标签

B529版本已升级1-2包,已经适配3-8包,请回归

wangbixing 添加协作者wangbixing
wangbixing 负责人wangbixing 修改为chentangyu
wangbixing 取消协作者chentangyu
wangbixing 任务状态TODO 修改为VALIDATION

B529版本回归通过
输入图片说明

i-robot 添加了
 
foruda
标签
chentangyu 任务状态VALIDATION 修改为DONE

登录 后才可以发表评论

状态
负责人
项目
里程碑
Pull Requests
关联的 Pull Requests 被合并后可能会关闭此 issue
分支
开始日期   -   截止日期
-
置顶选项
优先级
预计工期 (小时)
参与者(4)
7508424 tacyi139 1588073933
Python
1
https://gitee.com/mindspore/mindspore.git
git@gitee.com:mindspore/mindspore.git
mindspore
mindspore
mindspore

搜索帮助

344bd9b3 5694891 D2dac590 5694891