Yolov5: OSError: [WinError 126] The specified module could not be found

[asian3]

when I run detect.py. I meet the following Error:

File "E:\yolo\yolov5-master\utils\utils.py", line 20, in
from scipy.signal import butter, filtfilt
File "E:\yolo\yolov5-master\venv\lib\site-packages\scipy__init__.py", line 104, in
from . import _distributor_init
File "E:\yolo\yolov5-master\venv\lib\site-packages\scipy_distributor_init.py", line 61, in
WinDLL(os.path.abspath(filename))
File "C:\Users\xdef\AppData\Local\Programs\Python\Python36\lib\ctypes__init__.py", line 348, in __init__
self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] The specified module could not be found

[github-actions[bot]]

Hello @asian3, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

You might need to upgrade your scipy. You can also use one of our working environments:

Reproduce Our Environment

To access an up-to-date working environment (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled), consider a:

• GCP Deep Learning VM with $300 free credit offer: See our GCP Quickstart Guide
• Google Colab Notebook with 12 hours of free GPU time.
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide

[asian3]

You might need to upgrade your scipy. You can also use one of our working environments:

Reproduce Our Environment

To access an up-to-date working environment (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled), consider a:

• GCP Deep Learning VM with $300 free credit offer: See our GCP Quickstart Guide
• Google Colab Notebook with 12 hours of free GPU time.
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide

Thank you for your reply.But my scipy is the latest 1.5.0.It does not work .

[asian3]

AND.
When I use conda to build env,the following error happend:

pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
File "E:\yolo\yolov5-master\utils\utils.py", line 605, in non_max_suppression
i = torchvision.ops.boxes.nms(boxes, scores, iou_thres)
File "C:\Users\xdef.conda\envs\yolo5\lib\site-packages\torchvision\ops\boxes.py", line 36, in nms
return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
File "C:\Users\xdef.conda\envs\yolo5\lib\site-packages\torch_ops.py", line 61, in __getattr__
op = torch._C._jit_get_operation(qualified_op_name)
RuntimeError: No such operator torchvision::nms

[glenn-jocher]

Like I said, you can use one of our working environments.

Reproduce Our Environment

To access an up-to-date working environment (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled), consider a:

• GCP Deep Learning VM with $300 free credit offer: See our GCP Quickstart Guide
• Google Colab Notebook with 12 hours of free GPU time.
• Docker Image https://hub.docker.com/r/ultralytics/yolov5. See Docker Quickstart Guide

[Samll-Kosmos]

To solve the issue, in your venv

python -m pip uninstall scipy
python -m pip install scipy==1.4.1

Theres a problem with the new release of scipy

[asian3]

python -m pip install scipy==1.4.1

Thank you very much.It works well now with your method.