-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The 'bbox_iou' function on line 177 in 'yolov4.py' seems wrong #24
Comments
I also found the same problem, this may be the reason why the network training loss is nan |
do you have a solution to the issue? |
I have changed, But the loss of training is still nan. |
Yes, that function is definitely wrong. I changed that line to compute left_up coordinates, as well as the right_down coordinates. I also found in some implementations the iou is computed using the maximum between the value and an epsilon as this:
|
tensorflow-yolov4-tflite/core/yolov4.py
Line 187 in 9a4f98e
The box1 and box1 of this line of code should not be able to get the coordinates of the upper left corner of the overlapping area.
The text was updated successfully, but these errors were encountered: