xiyufeng2

作者你好，出现这个问题是您的readme中少写了一步：进入gliding vertex项目后也要执行python setup.py build develop。

你好！可视化结果infrence.py中，只有框，没有类别信息。代码里输出结果prediction中，也只有4个参数：hbox、rbbox、ratio、scores。请问如何生成并显示类别信息

loss = model(imgs.to(device), targets, requestPrecision=True)， IndexError: only integers, slices (`:`), ellipsis (`...`), None and long or byte Variables are valid indices (got numpy.float32) it seems like targets can't be float32.

> same problem, waiting for suggestion! c++ compile error （while execute command ‘bash compile_op.sh’）。change a computer is ok. >

so loss is changing like this, the train is effective?

plus the function 'ops.bfs_cluster'. These two functions are highly encapsulated by the C language and cannot understand the meaning。这两个函数都被C语言高度封装，无法理解意义

I find that the reconstruction quality is good in the outside environment whose view is very wide. But too many floaters in a room. Maybe the camera is too close...