Closed fengxingxiang closed 5 years ago
已解决,见问题 #37
不可以啊
---原始邮件--- 发件人: "紫晨"<notifications@github.com> 发送时间: 2019年9月6日(星期五) 晚上6:28 收件人: "PengyiZhang/SlimYOLOv3"<SlimYOLOv3@noreply.github.com>; 抄送: "Subscribed"<subscribed@noreply.github.com>; 主题: Re: [PengyiZhang/SlimYOLOv3] 大神,请问不经过sparsity训练可以直接prune吗? (#36)
已解决,见问题 #37
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
这个方法就是稀疏剪枝,不过也有别的不用稀疏的方法
---原始邮件--- 发件人: "紫晨"<notifications@github.com> 发送时间: 2019年9月6日(星期五) 晚上6:28 收件人: "PengyiZhang/SlimYOLOv3"<SlimYOLOv3@noreply.github.com>; 抄送: "Subscribed"<subscribed@noreply.github.com>; 主题: Re: [PengyiZhang/SlimYOLOv3] 大神,请问不经过sparsity训练可以直接prune吗? (#36)
已解决,见问题 #37
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
启动时报错 layer: 0 Traceback (most recent call last): File "prune.py", line 389, in
opt.perlayer_ratio,
File "prune.py", line 160, in test
m = getattr(module, 'batchnorm%d' % i) # batch_norm layer
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 591, in getattr
type(self).name, name))
AttributeError: 'Sequential' object has no attribute 'batch_norm_0'