CompliceU
CompliceU
@mzr1996 你好,我现在尝试对照VOC数据进行多标签任务,但是好像标签有问题,不知道可以不可以给一个较为完善的示例,非常感谢
@AngelaZha 不知道你成功了没有呢,我最近也打算尝试一下你的思路,可以交流一下,1215533585,这是我的QQ。我认为可以利用单摄像头进行跟踪,把特征和crop图等信息放到一个具有datbase概念的队列中,在另外的一个进程中进行消费处理,可以是聚类或者其他有效的方法。
@GeekAlexis Hello, if the camera I am using has overlapping areas, I don't know how to deal with this situation better.
@770258506 did you konw how to do about this ?
@yjxiong
@ManiaaJia @liruilong940607 Hello, I am trying to perform pose alignment. I don’t know if the author’s work requires pre-correction of the input image and the size of the pose.
Hello, I am using alphapose to estimate key points and perform pose alignment without segmentation. I don’t know how to modify it.
pip install dm-sonnet==1.23?? @FredlinT
@szxczyc I don't know how the effect of this loss function is now
@bigdoubi 我也遇到了你这个问题,不知道是这么解决的