[Bug] create_process - 82 - visualize onnxruntime model failed.

[jiangyuanJ]

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

i use the mmdeploy for mmseg the model inference,but there is a mistake.
AttributeError: module 'ctypes' has no attribute 'DLL'
11/18 16:27:36 - mmengine - ERROR - tools/deploy.py - create_process - 82 - visualize onnxruntime model failed.

Reproduction

python tools/deploy.py configs/mmseg/segmentation_onnxruntime_static-1024x2048.py my_maskformer_r50-d32_8xb2-160k_ade20k-512x512.py iter_10000.pth 100103.jpg --work-dir mmdeploy_models --show --dump-info

Environment

mmdeploy ==1.3.0 
onnxruntime ==1.15.1
onnxruntime-gpu==1.15.1
window10

Error traceback

(openmmlab) C:\Users\xxk\mmdeploy>python tools/deploy.py configs/mmseg/segmentation_onnxruntime_static-1024x2048.py my_maskformer_r50-d32_8xb2-160k_ade20k-512x512.py iter_10000.pth 100103.jpg --work-dir mmdeploy_models --show --dump-info
11/18 16:27:10 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
11/18 16:27:10 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "mmseg_tasks" registry tree. As a workaround, the current "mmseg_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
11/18 16:27:13 - mmengine - INFO - Start pipeline mmdeploy.apis.pytorch2onnx.torch2onnx in subprocess
11/18 16:27:16 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
11/18 16:27:16 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "mmseg_tasks" registry tree. As a workaround, the current "mmseg_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
Loads checkpoint by local backend from path: iter_10000.pth
11/18 16:27:16 - mmengine - WARNING - DeprecationWarning: get_onnx_config will be deprecated in the future.
11/18 16:27:16 - mmengine - INFO - Export PyTorch model to ONNX: mmdeploy_models\end2end.onnx.
E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\core\optimizers\function_marker.py:160: TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  ys_shape = tuple(int(s) for s in ys.shape)
E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\mmseg\models\segmentors\base.py:47: TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  img_shape = [int(val) for val in img_shape]
E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\mmseg\models\segmentors\base.py:61: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  if seg_logit.shape[1] == 1:
11/18 16:27:27 - mmengine - INFO - Execute onnx optimize passes.
11/18 16:27:27 - mmengine - WARNING - Can not optimize model, please build torchscipt extension.
More details: https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/experimental/onnx_optimizer.md
============= Diagnostic Run torch.onnx.export version 2.0.1+cu117 =============
verbose: False, log level: Level.ERROR
======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

11/18 16:27:28 - mmengine - INFO - Finish pipeline mmdeploy.apis.pytorch2onnx.torch2onnx
11/18 16:27:29 - mmengine - INFO - Start pipeline mmdeploy.apis.utils.utils.to_backend in main process
11/18 16:27:29 - mmengine - INFO - Finish pipeline mmdeploy.apis.utils.utils.to_backend
11/18 16:27:29 - mmengine - INFO - visualize onnxruntime model start.
11/18 16:27:35 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
11/18 16:27:35 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "mmseg_tasks" registry tree. As a workaround, the current "mmseg_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
11/18 16:27:35 - mmengine - WARNING - Failed to search registry with scope "mmseg" in the "backend_segmentors" registry tree. As a workaround, the current "backend_segmentors" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmseg" is a correct scope, or whether the registry is initialized.
2024-11-18:16:27:35 - root - ERROR - module 'ctypes' has no attribute 'DLL'
Traceback (most recent call last):
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\utils\utils.py", line 41, in target_wrapper
    result = target(*args, **kwargs)
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\apis\visualize.py", line 65, in visualize_model
    model = task_processor.build_backend_model(
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\mmseg\deploy\segmentation.py", line 157, in build_backend_model
    model = build_segmentation_model(
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\mmseg\deploy\segmentation_model.py", line 224, in build_segmentation_model
    backend_segmentor = __BACKEND_MODEL.build(
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmengine\registry\registry.py", line 570, in build
    return self.build_func(cfg, *args, **kwargs, registry=self)
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmengine\registry\build_functions.py", line 121, in build_from_cfg
    obj = obj_cls(**args)  # type: ignore
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\mmseg\deploy\segmentation_model.py", line 44, in __init__
    self._init_wrapper(
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\mmseg\deploy\segmentation_model.py", line 52, in _init_wrapper
    self.wrapper = BaseBackendModel._build_wrapper(
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\codebase\base\backend_model.py", line 65, in _build_wrapper
    return backend_mgr.build_wrapper(backend_files, device, input_names,
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\backend\onnxruntime\backend_manager.py", line 35, in build_wrapper
    return ORTWrapper(
  File "E:\PyTorch_learning\Miniconda\install\envs\openmmlab\lib\site-packages\mmdeploy\backend\onnxruntime\wrapper.py", line 51, in __init__
    ctypes.DLL(lib_path)
AttributeError: module 'ctypes' has no attribute 'DLL'
11/18 16:27:36 - mmengine - ERROR - tools/deploy.py - create_process - 82 - visualize onnxruntime model failed.