Open pop134 opened 4 years ago
As in the models.py:
https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/4ccef0ec8fe984e059378813e33b3740929e0c19/models.py#L446-L448
https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/4ccef0ec8fe984e059378813e33b3740929e0c19/models.py#L370
I'm I understanding this right? Cause I think the anchors masks here must be [6,7,8] due to the size of the features to detect small objects. Big thanks.
Hi @pop134, This confused me as well, Did you manage to get better results by modifying yolo1 to hold the biggest stride and anchor mask ? Thanks
As in the models.py:
https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/4ccef0ec8fe984e059378813e33b3740929e0c19/models.py#L446-L448
https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/4ccef0ec8fe984e059378813e33b3740929e0c19/models.py#L370
I'm I understanding this right? Cause I think the anchors masks here must be [6,7,8] due to the size of the features to detect small objects. Big thanks.