zk19971101

Results 5 comments of zk19971101

i encountered the same problem about torchtext. my anaconda env is : pytorch 1.12.0 torchtext 0.13.0 cuda 11.6

Thx, i found the reason of it, because i forgot to set the parameter 'mbunit'=ExpendMemoryUnit.

> > 终于成功了,虽然项目的效果差强人意 > > 你好,请问这个是什么问题呢? Usage: pip install [options] [package-index-options] ... pip install [options] -r [package-index-options] ... pip install [options] [-e] ... pip install [options] [-e] ... pip install...

我也遇到了这个问题,我猜测是设置的背景图像的问题,设置的背景图像是固定的,当人物在动的时候就会出现割裂。 i encounted the same problem, i guess this problem dirive from the fixed background image of the video.

> 对于问题1,我已经大概认定这是位姿,但是对于原视频一眨眼,推理的人脸就忽大忽小这个问题我还是比较困惑 请问是原始视频中每一帧图像的相机的RT矩阵(外参)吗?