zhuixunforever

Results 20 comments of zhuixunforever

@chris-nbi @RMalikM Same question. do you finish this function? could you provide a script. Thank you very much!

Sorry for the late reply. According to my understanding, delta in the second formula of Ep(8) is 'dist'. Am I getting this wrong?

@destiny311 @LucienXian I get the dataset by search "300W-LP" in Google, and you can find the download link of 300W-LP in the web http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm. I generate groundtruth position map just...

@KangolHsu the face(verdex indes) is fixed, so if you don't want the face of mouth, you can delete it.

I list the download link, and then use the browser (firefox / chrome), the download speed reaches 2~4m/s. To download automatically, I use chrono in chrome, and then import all...

@Jaychoukobbe @Z-Z-Han @yxlijun did you train your own dataset? or train coco/voc dataset by your self? did you success with this code? and how long had you been training??

Yeah, I use pytorch 0.4.1 on RTX 2080ti, with cuda 10 or cuda9.0, get a similar result. The same, I get 'THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=663 error=11 : invalid argument'. Therefore,...

I saw someone solve it by [“pip3 install -U https://download.pytorch.org/whl/cu100/torch-1.0.0-cp36-cp36m-linux_x86_64.whl”](https://github.com/pytorch/pytorch/issues/15797#issuecomment-472167754), and I will try it by "pip3 install -U https://download.pytorch.org/whl/cu90/torch-0.4.1-cp27-cp27m-linux_x86_64.whl". After I try it, I'll tell you the result.

Just installing pytorch0.4.1 by pip from [https://download.pytorch.org/whl/cu90/torch-0.4.1-cp27-cp27m-linux_x86_64.whl](https://download.pytorch.org/whl/cu90/torch-0.4.1-cp27-cp27m-linux_x86_64.whl) didn't work for me. I find someone solve the compatibility problem between 2080Ti and Pytorch0.4.1 by installe cuda9.2, I try it. And 'THCudaCheck...

The reason of RuntimeWarning is, the max timestamps of ins.csv large the max timestamps of stereo.timestamps in LOOP1(2014-06-23-15-41-25). I tried to remove the extra timestamps in stereo.timestamps, but that didn't...