a-haja

CIoU computation

1

I would like to ask about the computation of the CIoU. Based on https://www.programmersought.com/article/33648955485/ CIoU is defined as follows: > CIoU = **1** - IoU + dist(b, b_gt) / c**2...

@argusswift The current implementation of the main function in YoloV4Loss is unfortunately not correct. You need to adjust the following: https://github.com/argusswift/YOLOv4-pytorch/blob/d0a3b6553c22a7e45e218fb1b82465367e833792/model/loss/yolo_loss.py#L163 instead of `from model.build_model import Yolov4` and `net =...

Understanding Yolo_head.__decode()

1

@argusswift Can you please explain to us what Yolo_head.__decode() exactly does? https://github.com/argusswift/YOLOv4-pytorch/blob/a0627679f38af811a8311a3d12213fe789ce1e6b/model/head/yolo_head.py#L22 Is there a formel that you use for computing **p_de**? Thank you in advance

Hi Zijie, It would be nice if you can explain to me the following: 1) Why the **last** label shape in dataset.py (__creat_label function) is **6**+self.num_classes ? `label = [np.zeros((int(train_output_size[i]),...