起因：根据官方教程将PyTorch模型转换为了.engine的TensorRT格式以期提高加载和推理速度，在Windows10/RTX4060上没有任何问题，推理所需时间从20ms/frame降低到了8ms/frame，提升显著。

然而在Jetson Xavier NX上转换后，虽然转换过程没有报任何错误，但一旦想要导入模型来使用，就会报错：

WARNING ⚠️ Unable to automatically guess model task, assuming 'task=detect'. Explicitly define task for your model, i.e. 'task=detect', 'segment', 'classify','pose' or 'obb'.
Loading CCVision/train/yolov8n_epochs500_batch50/weights/best.engine for TensorRT inference...
[05/11/2024-18:23:11] [TRT] [I] Loaded engine size: 17 MiB
[05/11/2024-18:23:15] [TRT] [I] [MemUsageChange] Init cuDNN: CPU +342, GPU +323, now: CPU 700, GPU 3714 (MiB)
[05/11/2024-18:23:15] [TRT] [I] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +22, now: CPU 0, GPU 22 (MiB)
[05/11/2024-18:23:15] [TRT] [I] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 683, GPU 3714 (MiB)
[05/11/2024-18:23:15] [TRT] [I] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +596, now: CPU 0, GPU 618 (MiB)
/usr/lib/python3.8/dist-packages/tensorrt/__init__.py:166: FutureWarning: In the future `np.bool` will be defined as the corresponding NumPy scalar.
  bool: np.bool,
Traceback (most recent call last):
  File "yolodetect.py", line 10, in <module>
    results = model(stream=True, source=0, show=True)
  File "/home/jetson/.local/lib/python3.8/site-packages/ultralytics/engine/model.py", line 176, in __call__
    return self.predict(source, stream, **kwargs)
  File "/home/jetson/.local/lib/python3.8/site-packages/ultralytics/engine/model.py", line 445, in predict
    self.predictor.setup_model(model=self.model, verbose=is_cli)
  File "/home/jetson/.local/lib/python3.8/site-packages/ultralytics/engine/predictor.py", line 297, in setup_model
    self.model = AutoBackend(
  File "/home/jetson/.local/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/jetson/.local/lib/python3.8/site-packages/ultralytics/nn/autobackend.py", line 273, in __init__
    dtype = trt.nptype(model.get_binding_dtype(i))
  File "/usr/lib/python3.8/dist-packages/tensorrt/__init__.py", line 166, in nptype
    bool: np.bool,
  File "/home/jetson/.local/lib/python3.8/site-packages/numpy/__init__.py", line 305, in __getattr__
    raise AttributeError(__former_attrs__[attr])
AttributeError: module 'numpy' has no attribute 'bool'.
`np.bool` was a deprecated alias for the builtin `bool`. To avoid this error in existing code, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
    https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations

搜索了一下，Github上也有人遇到这个问题，共同点是都是Ubuntu系统：

https://github.com/ultralytics/ultralytics/issues/1128

降级到1.23.5确实可以解决这个问题，但pip也警告：

jetson@ubuntu:~/RoboContest/#CyberCartNX$ pip install numpy==1.23.5
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://mirror.sjtu.edu.cn/pypi/web/simple
Collecting numpy==1.23.5
  Downloading https://mirror.sjtu.edu.cn/pypi-packages/bf/d1/1017fe3f5d65c4fe054a793f18f940d913868bb2846a02d3f6244a829a30/numpy-1.23.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (14.0 MB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 14.0/14.0 MB 4.3 MB/s eta 0:00:00
Installing collected packages: numpy
  Attempting uninstall: numpy
    Found existing installation: numpy 1.19.5
    Uninstalling numpy-1.19.5:
      Successfully uninstalled numpy-1.19.5
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
onnxruntime-gpu 1.17.0 requires numpy>=1.24.4, but you have numpy 1.23.5 which is incompatible.
Successfully installed numpy-1.23.5

也就是说，1.23.5对于某些包来说还是偏低的……但至少模型可以加载并推理了。

问题暂时解决，如果后续还有别的问题再更新。