get nan in box list when inference

[BELZHANG]

My dataset only has two classes so I changed the channel num from 255 to 21 in the head, is this the only part you need to take care when train your own dataset?

[Tianxiaomo]

You can take a look at the latest code,you just need to set a value to the n_classes.

class Yolov4(nn.Module):
    def __init__(self, yolov4conv137weight=None, n_classes = 80):
        super().__init__()

class Yolo_loss(nn.Module):
    def __init__(self, n_classes=80, n_anchors=3, device=None, batch=2):
        super(Yolo_loss, self).__init__()