JYChen
JYChen
@sebkim Hi. I'm facing a similar problem too. The performance and output of the same model are weird on XS and XS MAX, while the model works fine on other...
> @zoooo0820 Is it possible for you to share your model so that we can reproduce the issue at our end? Any reproducible toy model would also work. Sorry for...
正负样本的区分是在同一个场景中,按动作不同进行的区分。实际数据存在多个场景,这些场景中均按上述方法区分了正负样本没具体数据说明可以参考文档中的介绍。 在实际使用中,尽量保证场景和训练数据一致以保证效果
请检查一下设置的batchsize大小和数据集本身的数量呢
辛苦具体描述下遇到的问题是什么,方便我们定位下问题
@lilinhan1998 https://github.com/PaddlePaddle/PaddleVideo/tree/develop/applications/PPHuman#readme 请参考这个链接,具体还有不清楚的地方可以再提出来
I met the same problem too. Did you solve the problem? @ypflll @wangbm
@eyiztan Hi, I'm trying to get the result the paper claimed, but I only get nme about 0.06 on 300W. I also noticed your discussion with the author of Wingloss...
是的,一个视频片段会转化为一个骨骼点序列(每一帧都有人物的一组骨骼点坐标)
请问c++ PaddleInference的版本是什么呢