zwyking
zwyking
你好，请问这个问题解决了么？
我在训练的时候也遇到了这个问题😂，但是这个score出现0的话也不会导致nan叭
你好，我想问一下您的训练loss，最后大概是在多少呢？
thanks for your advice! It works~ ------------------ Original ------------------ From: ***@***.***>; Send time: Thursday, Apr 8, 2021 10:33 PM ***@***.***>; ***@***.***>; ***@***.***>; Subject: Re: [zhanghang1989/PyTorch-Encoding] gtx3090，cuda=11.0，pytorch=1.7, 报错nvcc fatal : Unsupported gpu architecture 'compute_86'...
> okay , i try it again.... > […](#) > ------------------ 原始邮件 ------------------ 发件人: "zhanghang1989/PyTorch-Encoding" ***@***.***>; 发送时间: 2021年4月8日(星期四) 晚上11:53 ***@***.***>; ***@***.******@***.***>; 主题: Re: [zhanghang1989/PyTorch-Encoding] gtx3090，cuda=11.0，pytorch=1.7, 报错nvcc fatal : Unsupported gpu architecture 'compute_86' (#383) Hi....
Have the same question as above.
This is a rubbish work!
> We want to report to ICCV officials. We hope you can join us too.
Hi, I have the same question! Have you find the way to generate them (.mat, landmark.txt)?
> I wrote a test script which solved the hanging problem. I guess there is something wrong with reduce function. > > Please refer to the script: > https://gist.github.com/shuuchen/7463009370e9ddf77e649f3fec259024 >...