Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
Join GitHub today
GitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together.
Sign upx86和arm上的差异性问题 #295
Open
x86和arm上的差异性问题 #295
Labels
Comments
|
方便的话，能提供下模型及测试代码吗？以便我们进行bug修复，谢谢。 |
|
你好，这是我的代码和模型，麻烦了，如果可以的话，加我QQ：405631964，直接交流，谢谢
…------------------ 原始邮件 ------------------
发件人: "BUG1989"<notifications@github.com>;
发送时间: 2020年5月10日(星期天) 晚上10:04
收件人: "OAID/Tengine"<Tengine@noreply.github.com>;
抄送: "肖大大"<405631964@qq.com>;"Author"<author@noreply.github.com>;
主题: Re: [OAID/Tengine] x86和arm上的差异性问题 (#295)
方便的话，能提供下模型及测试代码吗？以便我们进行bug修复，谢谢。
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
从QQ邮箱发来的超大附件
zhs_face_tengine.zip (53.63M, 2020年06月10日 09:45 到期)进入下载页面：http://mail.qq.com/cgi-bin/ftnExs_download?t=exs_ftn_download&k=7b3530638393c0c4ee461d7b1261571702560257065404081f070157514c510f05531d5a06035015030152520d52005a56030553347565425a466f055502006746505e045d0f0016485c406309&code=250c4ae8
|
|
你好，请问代码测试了吗，问题是否已经解决了呢？？？
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
做人脸识别，我把检测的多张人脸拼成n1128128的矩阵,在x86运行没有问题，在arm上运行识别不到人，经过我跟踪打印，发现arm的多人提取的特征只有一张图片长度(即128128)的数值正常，其他后续的都为nan，代码完全相同，图片完全相同，但是x86上没有任何问题，麻烦修订一下，解决这个问题！！！！