Difference conf result between torch.hub.load() and detect.py in same model #12481
Unanswered
hayamaakiro
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I use torch.hub.load() and detect.py separately for object detection, using the same model. However, the detected confidence values (conf) are different. When using torch.hub.load(), conf values are often below 0.1, but when using detect.py, conf values can range between 0.2 and 0.5. Why is this happening?
Beta Was this translation helpful? Give feedback.
All reactions