IndexError: index 0 is out of range

[Louis24]

首先谢谢您的教程，我最近在看网络裁剪，然后找到了这
https://blog.csdn.net/m0_53608998/article/details/117687416

在运行时发现少了很多文件，我就从

repo

https://github.com/ZJU-lishuang/yolov5_prune

缺省文件从下面找

https://github.com/ZJU-lishuang/yolov5-v4
https://github.com/ultralytics/yolov5

然后我直接裁剪发现
IndexError: index 0 is out of range

我重新训练的时候也是报错，请问是什么问题呢

Traceback (most recent call last):
File "train.py", line 520, in
train(hyp, opt, device, tb_writer, wandb)
File "train.py", line 86, in train
model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc).to(device) # create
File "C:\Zero\Python\yolov5_prune-4\models\yolo.py", line 80, in init
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
File "C:\Zero\Python\yolov5_prune-4\models\yolo.py", line 110, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "C:\Zero\Python\yolov5_prune-4\models\yolo.py", line 130, in forward_once
x = m(x) # run
File "C:\Users\LOUIS\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Zero\Python\yolov5_prune-4\models\yolo.py", line 37, in forward
x[i] = self.mi # conv
File "C:\Users\LOUIS\Anaconda3\lib\site-packages\torch\nn\modules\container.py", line 164, in getitem
return self._modules[self._get_abs_string_index(idx)]
File "C:\Users\LOUIS\Anaconda3\lib\site-packages\torch\nn\modules\container.py", line 154, in _get_abs_string_index
raise IndexError('index {} is out of range'.format(idx))
IndexError: index 0 is out of range

Process finished with exit code 0

[ZJU-lishuang]

目前我又重新复现了该项目，补充了缺少的文件，可以重新尝试一下

[Louis24]

好哦 多谢啦 我在出差 回去试试 您有qq微信嘛 我目前还有些问题 在准备面试 希望不吝赐教 Thank you very much. Sincerely yours Yexing Li

…

________________________________ From: ZJU-lishuang ***@***.***> Sent: 19 October 2021 02:18 To: ZJU-lishuang/yolov5_prune ***@***.***> Cc: Louis ***@***.***>; Author ***@***.***> Subject: Re: [ZJU-lishuang/yolov5_prune] IndexError: index 0 is out of range (#59) 目前我又重新复现了该项目，补充了缺少的文件，可以重新尝试一下 ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#59 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AEO2FABREAHVRICVKWUXUQ3UHULVXANCNFSM5FUTXAYA>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.

[ZJU-lishuang]

网络结构没对上，旧版本只支持yolov5s模型