[Bug]: ONNX转mindir文件后离线推理报错

### 问题描述

ONNX转mindir文件后 离线推理报错
Init mindor model:  /home/ma-user/ModelZoo-PyTorch/ACL_PyTorch/built-in/cv/SAM/models/mindir/encoder_bs1_atten_fp32-16_sub.mindir
原始图像形状: (1200, 1800, 3)
处理后矩阵的形状: (1, 3, 1024, 1024)
处理后矩阵的数据类型: float32
input data shape:  (1, 3, 1024, 1024)
^C[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.142 [mindspore/lite/src/extendrt/kernel/ascend/model/model_process.cc:1340] PredictFromHost] Execute Model Failed, ret = 507011, detail:EZ9999: Inner Error!
        Op execute failed. origin_op_name [/blocks.0/Pad], op_name [/blocks.0/Pad], error_info: task_id 8, stream_id 43, tid 52890, device_id 0, retcode 0x7bc83[FUNC:ErrorTrackingCallback][FILE:error_tracking.cc][LINE:116]
EZ9999: [PID: 52890] 2025-09-15-16:26:11.593.140 Aicore kernel execute failed, device_id=0, stream_id=43, report_stream_id=44, task_id=8, flip_num=0, fault kernel_name=te_padv3_4e06002a78646ab881209ff0134ac3e03304b174777fd674a11f6ba20fe164ba7857d1e692d01a8cf9865dcd63f1dd69ff399aca037ae25ee4513d74b23f6ed3_static_bin, fault kernel info ext=te_padv3_4e06002a78646ab881209ff0134ac3e03304b174777fd674a11f6ba20fe164ba__kernel0, program id=8, hash=447030594573471714.[FUNC:GetError][FILE:stream.cc][LINE:1119]
        TraceBack (most recent call last):
       [AIC_INFO] after execute:args print end[FUNC:GetError][FILE:stream.cc][LINE:1119]
       [AIC_INFO] after execute:mixCtx print end[FUNC:GetError][FILE:stream.cc][LINE:1119]
       Fail to synchronize forbbiden stream, retCode=0x7150050![FUNC:SynchronizeExecute][FILE:model.cc][LINE:759]
       Model synchronize execute failed, model_id=39, timeout=-1![FUNC:GetStreamToSyncExecute][FILE:model.cc][LINE:821]
        rtModelExecuteSync execute failed, reason=[the model stream execute failed][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:53]
       [Exec][Model]Execute model failed, ge result[507011], modelId[1][FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
       [Exec][Model]modelId[1] execute failed, result[507011][FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.220 [mindspore/lite/src/extendrt/kernel/ascend/model/model_infer.cc:182] Inference] Model predict failed
[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.236 [mindspore/lite/src/extendrt/kernel/ascend/src/custom_ascend_kernel.cc:279] Launch] Custom kernel execute failed.
[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.253 [mindspore/lite/src/extendrt/session/single_op_session.cc:529] RunGraph] Failed to launch kernel
[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.295 [mindspore/lite/src/extendrt/cxx_api/model/model_impl.cc:852] Predict] ModelImpl::Predict RunGraph failed!ret = Common error code.
Traceback (most recent call last):
  File "/home/ma-user/ModelZoo-PyTorch/ACL_PyTorch/built-in/cv/SAM/./py_code/1_model_infer_mindir.py", line 61, in <module>
    model_outputs = ms_model.Predict(data)
  File "/home/ma-user/ModelZoo-PyTorch/ACL_PyTorch/built-in/cv/SAM/./py_code/1_model_infer_mindir.py", line 49, in Predict
    outputs = self.model.predict(model_inputs)
  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindspore_lite/model.py", line 451, in predict
    return super(Model, self).predict(inputs_tensor, outputs)
  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindspore_lite/base_model.py", line 116, in predict
    predict_result = self._model.predict(_inputs, _outputs)
KeyboardInterrupt

### 环境信息

- **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
> /device GPU
> /device CPU
 910B4

- **Software Environment / 软件环境 (Mandatory / 必填)**:
-- MindSpore version (e.g., 2.0.0) :
-- Python version (e.g., Python 3.7.5) :
-- OS platform and distribution (e.g., Linux Ubuntu 16.04):
-- GCC/Compiler version (if compiled from source):

- **Execute 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 pynative
> /mode graph
 不涉及

### 关联用例

无

### 重现步骤

无

### 预期结果

可以正常推理

### 日志/截图

Init mindor model:  /home/ma-user/ModelZoo-PyTorch/ACL_PyTorch/built-in/cv/SAM/models/mindir/encoder_bs1_atten_fp32-16_sub.mindir
原始图像形状: (1200, 1800, 3)
处理后矩阵的形状: (1, 3, 1024, 1024)
处理后矩阵的数据类型: float32
input data shape:  (1, 3, 1024, 1024)
^C[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.142 [mindspore/lite/src/extendrt/kernel/ascend/model/model_process.cc:1340] PredictFromHost] Execute Model Failed, ret = 507011, detail:EZ9999: Inner Error!
        Op execute failed. origin_op_name [/blocks.0/Pad], op_name [/blocks.0/Pad], error_info: task_id 8, stream_id 43, tid 52890, device_id 0, retcode 0x7bc83[FUNC:ErrorTrackingCallback][FILE:error_tracking.cc][LINE:116]
EZ9999: [PID: 52890] 2025-09-15-16:26:11.593.140 Aicore kernel execute failed, device_id=0, stream_id=43, report_stream_id=44, task_id=8, flip_num=0, fault kernel_name=te_padv3_4e06002a78646ab881209ff0134ac3e03304b174777fd674a11f6ba20fe164ba7857d1e692d01a8cf9865dcd63f1dd69ff399aca037ae25ee4513d74b23f6ed3_static_bin, fault kernel info ext=te_padv3_4e06002a78646ab881209ff0134ac3e03304b174777fd674a11f6ba20fe164ba__kernel0, program id=8, hash=447030594573471714.[FUNC:GetError][FILE:stream.cc][LINE:1119]
        TraceBack (most recent call last):
       [AIC_INFO] after execute:args print end[FUNC:GetError][FILE:stream.cc][LINE:1119]
       [AIC_INFO] after execute:mixCtx print end[FUNC:GetError][FILE:stream.cc][LINE:1119]
       Fail to synchronize forbbiden stream, retCode=0x7150050![FUNC:SynchronizeExecute][FILE:model.cc][LINE:759]
       Model synchronize execute failed, model_id=39, timeout=-1![FUNC:GetStreamToSyncExecute][FILE:model.cc][LINE:821]
        rtModelExecuteSync execute failed, reason=[the model stream execute failed][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:53]
       [Exec][Model]Execute model failed, ge result[507011], modelId[1][FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
       [Exec][Model]modelId[1] execute failed, result[507011][FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]

[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.220 [mindspore/lite/src/extendrt/kernel/ascend/model/model_infer.cc:182] Inference] Model predict failed
[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.236 [mindspore/lite/src/extendrt/kernel/ascend/src/custom_ascend_kernel.cc:279] Launch] Custom kernel execute failed.
[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.253 [mindspore/lite/src/extendrt/session/single_op_session.cc:529] RunGraph] Failed to launch kernel
[ERROR] ME(52890,ffffa4f70020,python):2025-09-15-16:26:11.598.295 [mindspore/lite/src/extendrt/cxx_api/model/model_impl.cc:852] Predict] ModelImpl::Predict RunGraph failed!ret = Common error code.
Traceback (most recent call last):
  File "/home/ma-user/ModelZoo-PyTorch/ACL_PyTorch/built-in/cv/SAM/./py_code/1_model_infer_mindir.py", line 61, in <module>
    model_outputs = ms_model.Predict(data)
  File "/home/ma-user/ModelZoo-PyTorch/ACL_PyTorch/built-in/cv/SAM/./py_code/1_model_infer_mindir.py", line 49, in Predict
    outputs = self.model.predict(model_inputs)
  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindspore_lite/model.py", line 451, in predict
    return super(Model, self).predict(inputs_tensor, outputs)
  File "/home/ma-user/anaconda3/envs/PyTorch-2.1.0/lib/python3.10/site-packages/mindspore_lite/base_model.py", line 116, in predict
    predict_result = self._model.predict(_inputs, _outputs)
KeyboardInterrupt

### 备注

MindSpore/models

内容风险标识

评论 (2)

MindSpore/models .gitee-modal { width: 500px !important; }

内容风险标识