YOLOm-ASFF问题

[bzha5848]

你好！

我在修改的时候遇到如下问题，请问有什么办法可以解决吗？

[positive666]

你好！

我在修改的时候遇到如下问题，请问有什么办法可以解决吗？

这个是你的hyps的训练yaml中 没有给这个字段 你加上就行了

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[Grenaf]

up您好使用yolov5-p2搭配asff报错：
Traceback (most recent call last):
File "I:/tph-yolov5/train.py", line 630, in
main(opt)
File "I:/tph-yolov5/train.py", line 527, in main
train(opt.hyp, opt, device, callbacks)
File "I:/tph-yolov5/train.py", line 126, in train
model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
File "I:\tph-yolov5\models\yolo.py", line 186, in init
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
File "I:\tph-yolov5\models\yolo.py", line 204, in forward
return self._forward_once(x, profile, visualize) # single-scale inference, train
File "I:\tph-yolov5\models\yolo.py", line 227, in _forward_once
x = m(x) # run
File "I:\tph-yolov5\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "I:\tph-yolov5\models\yolo.py", line 114, in forward
x[i] = self.mi # conv
IndexError: list index out of range

进程已结束，退出代码为 1
原始的yolov5s(三尺度检测头)是不报错的，ASFF_Detect可以支持四尺度检测头吗(yolov5-p2)