用户您好，请详细描述您所遇到的问题：
- 系统软件版本：x3pi_ubuntu_v1.0.2
- 问题涉及的技术领域： onnx->bin
- 问题描述： python 端推理异常
```shell
[C][5004][08-08][11:09:09:639][configuration.cpp:51][EasyDNN]EasyDNN version: 0.3.5
[BPU_PLAT]BPU Platform Version(1.3.1)!
[HBRT] set log level as 0. version = 3.13.27
ioctl read error, ret = -1 error = 121
keros_i2c_read failed
ioctl write error, ret = -1 error = 121
keros_i2c_write failed
ioctl write error, ret = -1 error = 121
keros_i2c_write failed
ioctl read error, ret = -1 error = 121
keros_i2c_read failed
ioctl read error, ret = -1 error = 121
keros_i2c_read failed
ioctl read error, ret = -1 error = 121
keros_i2c_read failed
ioctl read error, ret = -1 error = 121
keros_i2c_read failed
ioctl read error, ret = -1 error = 121
keros_i2c_read failed
[000:000] (keros_util.cpp:99): keros_authentication failed, ret = 0
[000:000] (configuration.cpp:147): Keros key init failed.
[DNN] Runtime version = 1.8.4_(3.13.27 HBRT)
[HorizonRT] The model builder version = 1.8.7
tensor type: NV12_SEPARATE
data type: uint8
layout: NCHW
shape: (1, 3, 640, 640)
hbrtErrorInvalidBatchCount
file=f3a31eef122a41bb11cce71188f99333fc1ffdf9
3171
hbrtErrorIllegalHBMHandle
file=7b0c25e023bb537c72d2b9349b00937143a7e5f8
354
[000:880] (hbm_exec_plan.cpp:758): [HBRT ERROR] hbrtErrorInvalidBatchCount
[000:880] (multi_model_task.cpp:1229): RiContinue failed
[000:880] (cpu_schedule.cpp:72): Generate funccall failed, task:Task(task_id:0, core_id:2, priority:0,estimate execute time:66713, desc: [yolov5n_yaml], time_points: [7228472303,7228472399,0])
hbrtErrorRiIsNotInUse
file=f3a31eef122a41bb11cce71188f99333fc1ffdf9
4135
[000:880] (hbm_exec_plan.cpp:397): [HBRT ERROR] hbrtErrorRiIsNotInUse
[000:880] (multi_model_task.cpp:1288): RiDestroy failed
【WaitInferDone failed】
Traceback (most recent call last):
File “python_infer.py”, line 71, in
outputs = models[0].forward(nv12)
RuntimeError: Run model failed!
【INFO】: Offload model “yolov5n_yaml” Successfully.
```
转换模型时有处报错，但是模型转换成功了。
```shell
2022-08-08 11:21:49.630702471 [E:onnxruntime:, sequential_executor.cc:183 Execute] Non-zero status code returned while running Reshape node. Name:‘Reshape_232’ Status Message: /home/jenkins/workspace/model_convert/onnxruntime/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:43 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, std::vector&) gsl::narrow_cast<int64_t>(input_shape.Size()) == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{8,255,20,20}, requested shape:{1,3,85,20,20}
```