skelact
skelact copied to clipboard
hikvision-research
Where is the skeletonMix SkeletonMix strategy used in this paper by ta-cnn in the code
A skeletonMix strategy is used in the tacnn paper, but I didn't see this part of the code when I read the code of tacnn. I didn't find it. Could you please point me to which lines of code in which file? thank you very much
In this repo, we only port the Ta-CNN network architecture, which is the major contribution of the paper. Implementation of SkeletonMix is left as future work. And any contribution from the community is welcome.
OK, thanks for your prompt reply.
------------------ 原始邮件 ------------------ 发件人: "Qiaoyong @.>; 发送时间: 2022年9月17日(星期六) 中午11:21 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [hikvision-research/skelact] Where is the skeletonMix SkeletonMix strategy used in this paper by ta-cnn in the code (Issue #1)
In this repo, we only port the Ta-CNN network architecture, which is the major contribution of the paper. Implementation of SkeletonMix is left as future work. And any contribution from the community is welcome.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Hello, the skeletonMix is implemented based on the 8th formula in the Ta-CNN's paper, and 1/16 of samples in a batch is generated with skeletonMix. The data is generated by randomly combining the upper body and the lower body of two different samples, and the label is the weighted sum of the one-hot encodings. Both the code and the result are easy to reproduce. If you have any questions, please contact with me.
Hello, the skeletonMix is implemented based on the 8th formula in the Ta-CNN's paper, and 1/16 of samples in a batch is generated with skeletonMix. The data is generated by randomly combining the upper body and the lower body of two different samples, and the label is the weighted sum of the one-hot encodings. Both the code and the result are easy to reproduce. If you have any questions, please contact with me.
您好 非常感谢您提供这么优质的一篇论文 其中我对skeletonMix策略很感兴趣，看了您提供的公式，但是还是不知道如何实现 如果可以的话 您方便提供一下源码嘛？非常感谢！
