Loading custom model does not work

[zkytony]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

No response

Bug

Previously, I can load a custom pretrained model like this:

torch.hub.load('ultralytics/yolov5', 'custom', path='path/to/model.pt')

However, after some recent developments (see issues below for related problems that occur after those developments).

• Why do I suddenly need to pip install the ultralytics library to get yolov5 from torch hub? #11544
• I got an hubconf.py error while loading my best.pt saved model #11481
• Load YOLOv5 from PyTorch Hub - TypeError: 'module' object is not callable #11448
• Exception: [Errno 2] No such file or directory: 'lib\\best.pt'. Cache may be out of date, try force_reload=True or see https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading for help.  #11530
  the above line of code does not work any more. Running it I get

Exception: [Errno 20] Not a directory: 'path/to/model.py'. Cache may be out o
f date, try `force_reload=True` or see https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_mode
l_loading for help.

I followed the suggestion and add force_reload=True:

torch.hub.load('ultralytics/yolov5', 'custom', path='path/to/model.pt', force_reload=True)

I am getting the SAME error:

Exception: [Errno 20] Not a directory: 'path/to/model.py'. Cache may be out of date, try `force_reload=True` or see https://docs.ultralytics.com
/yolov5/tutorials/pytorch_hub_model_loading for help.

What is going on with yolov5?

Environment

• YOLOv5
• ubuntu 22.04
• python 3.10.6
• torch 1.13.1+cu17

Minimal Reproducible Example

torch.hub.load('ultralytics/yolov5', 'custom', path='path/to/model.pt')

Choose a model path to replace 'path/to/model.pt'

Additional

No

Are you willing to submit a PR?

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

[zkytony]

Never mind. My path was wrong and I didn't realize it sorry:(

This may be helpful to others who run into a similar situation.

[glenn-jocher]

@zkytony no worries at all! It's great to hear that you were able to solve the issue. Don't hesitate to reach out if you have any further questions or concerns. Thank you for your support and happy coding!

[developerlaborotory]

I just had to reset my pc xD

[glenn-jocher]

@developerlaborotory not a problem at all! Sometimes a reset can help with unforeseen issues. If you have any further questions or run into any other problems, feel free to ask. Happy coding!