Open yuxx0218 opened 4 years ago
Maybe he's still working on it
I think there is support for CIOU: https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/fe45fb64ba4c21130643f9b2569da7bb667356b3/train.py#L41-L127
I think there is support for CIOU:
Thank you. I think you are right. Look forward to a complete version of YOLO v4.
It seems to me that bboxes_iou
are used only for matching prediction and ground truth bboxes? The actual loss function seems to use only binary cross entropy and mse . Am I missing something here?
https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/4ccef0ec8fe984e059378813e33b3740929e0c19/train.py#L265-L267
No CIOU Loss, no Lable Smoothing, no DropBlock Regularization, no Self-Adversarial Training, no DIOU NMS, no....... It is defnitely a YOLO v3 replacing the backbone/neck/head.