[Bug] infer yolox onnx model used by python infrence sdk failed in new linux server

[PancakeAwesome]

Checklist

• I have searched related issues but cannot get the expected help.
• 2. I have read the FAQ documentation but cannot get the expected help.
• 3. The bug has not been fixed in the latest version.

Describe the bug

code running until below:
bboxes, labels, _ = detector(img)
with errors:
[2023-06-07 10:00:27.160] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "yolox_s_fast_1xb32-300e-rtmdet-hyp/"
[2023-06-07 10:00:27.207] [mmdeploy] [error] [ort_net.cpp:205] unhandled exception when creating ORTNet: /onnxruntime_src/onnxruntime/core/platform/posix/env.cc:142 onnxruntime::{anonymous}::PosixThread::PosixThread(const char*, int, unsigned int ()(int, Eigen::ThreadPoolInterface), Eigen::ThreadPoolInterface*, const onnxruntime::ThreadOptions&) pthread_setaffinity_np failed

[2023-06-07 10:00:27.207] [mmdeploy] [error] [net_module.cpp:54] Failed to create Net backend: onnxruntime, config: {
"context": {
"device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": false,
"module": "Net",
"name": "yolodetector",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
[2023-06-07 10:00:27.207] [mmdeploy] [error] [task.cpp:99] error parsing config: {
"context": {
"device": "",
"model": "",
"stream": ""
},
"input": [
"prep_output"
],
"input_map": {
"img": "input"
},
"is_batched": false,
"module": "Net",
"name": "yolodetector",
"output": [
"infer_output"
],
"output_map": {},
"type": "Task"
}
load detector>>>>>>>>>>
段错误

Reproduction

image = Image.open(args.image_path)
image = image.convert("RGB")
image = np.array(image)[:, :, ::-1]
print(image.shape)
print(image)
detector = Detector(
model_path=args.model_path, device_name=args.device_name)
print("load detector>>>>>>>>>>")
bboxes, labels, masks = detector(image)

Environment

mmdeploy 1.1.0
mmdeploy-runtime 1.1.0
 $LD_LIBRARY_PATH:/home/admin/model_repository/9835a5de374c8ed1-model/tools/onnxruntime-linux-x64-1.8.1/lib:/usr/local/lib/python3.8/site-packages/mmdeploy_runtime/

Error traceback

[2023-06-07 10:00:27.160] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "yolox_s_fast_1xb32-300e-rtmdet-hyp/"
[2023-06-07 10:00:27.207] [mmdeploy] [error] [ort_net.cpp:205] unhandled exception when creating ORTNet: /onnxruntime_src/onnxruntime/core/platform/posix/env.cc:142 onnxruntime::{anonymous}::PosixThread::PosixThread(const char*, int, unsigned int (*)(int, Eigen::ThreadPoolInterface*), Eigen::ThreadPoolInterface*, const onnxruntime::ThreadOptions&) pthread_setaffinity_np failed

[2023-06-07 10:00:27.207] [mmdeploy] [error] [net_module.cpp:54] Failed to create Net backend: onnxruntime, config: {
  "context": {
    "device": "<any>",
    "model": "<any>",
    "stream": "<any>"
  },
  "input": [
    "prep_output"
  ],
  "input_map": {
    "img": "input"
  },
  "is_batched": false,
  "module": "Net",
  "name": "yolodetector",
  "output": [
    "infer_output"
  ],
  "output_map": {},
  "type": "Task"
}
[2023-06-07 10:00:27.207] [mmdeploy] [error] [task.cpp:99] error parsing config: {
  "context": {
    "device": "<any>",
    "model": "<any>",
    "stream": "<any>"
  },
  "input": [
    "prep_output"
  ],
  "input_map": {
    "img": "input"
  },
  "is_batched": false,
  "module": "Net",
  "name": "yolodetector",
  "output": [
    "infer_output"
  ],
  "output_map": {},
  "type": "Task"
}
load detector>>>>>>>>>>
段错误

[PancakeAwesome]

@irexyc @RunningLeon pleasethank you

[RunningLeon]

@PancakeAwesome Could you post here your env by running python tools/check_env.py?

[PancakeAwesome]

@PancakeAwesome Could you post here your env by running python tools/check_env.py?

I'm afraid I can't provide check_env.py results at the moment. mmcv is difficult to install
But what kind of environmental information do you need that I can output manually

[irexyc]

Not sure if it is related to daquexian/onnx-simplifier#171.

May use pure onnxruntime api to test if the error still exist.