AttributeError: module 'numpy.linalg._umath_linalg' has no attribute '_ilp64'

Search before asking

• I have searched the Roboflow Notebooks issues and found no similar bug report.

Notebook name

how-to-detect-and-count-objects-in-polygon-zone.ipynb

Bug

Using cache found in /root/.cache/torch/hub/ultralytics_yolov5_master
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
[<ipython-input-23-d827f2069f82>](https://localhost:8080/#) in <cell line: 3>()
      1 import torch
      2 
----> 3 model = torch.hub.load('ultralytics/yolov5', 'yolov5x6')

12 frames
[/usr/local/lib/python3.10/dist-packages/numpy/testing/_private/utils.py](https://localhost:8080/#) in <module>
     55 IS_PYSTON = hasattr(sys, "pyston_version_info")
     56 HAS_REFCOUNT = getattr(sys, 'getrefcount', None) is not None and not IS_PYSTON
---> 57 HAS_LAPACK64 = numpy.linalg._umath_linalg._ilp64
     58 
     59 _OLD_PROMOTION = lambda: np._get_promotion_state() == 'legacy'

AttributeError: module 'numpy.linalg._umath_linalg' has no attribute '_ilp64'

Environment

-Google colab
https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-detect-and-count-objects-in-polygon-zone.ipynb#scrollTo=0EL4o_eOQmej
Advanced YOLOv5 Market Square Example

Minimal Reproducible Example

import torch

model = torch.hub.load('ultralytics/yolov5', 'yolov5x6')

Additional

just running the official demo in this link

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

Start with notebooks/how-to-detect-and-count-objects-in-polygon-zone.ipynb and the cell containing torch.hub.load('ultralytics/yolov5', 'yolov5x6'); run the minimal example in Google Colab to reproduce the NumPy traceback. Trace the notebook's dependency environment and verify that the official demo runs without the AttributeError.