TJZhengJuepeng comments

Results 9 comments of


                                            TJZhengJuepeng

Training problem

I met the same problem, have you solved it?

When I want to use the code of PSANet， I meet this error subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1. . need help. thanks.

I met the same problem, have you solved it? THANKS!

Nontype error when run demo and train

I met the same problem, have you fixed it?

Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED

I met the same problem, have you fixed it? thanks a lot~

Check failed: status == CUDNN_STATUS_SUCCESS (8 vs. 0) CUDNN_STATUS_EXECUTION_FAILED

把make文件里的cudnn注释掉试试？ On 01/21/2019 13:51, gaojx wrote: @tjzjp Hello, have you solve the problem? Thank you! —You are receiving this because you were mentioned.Reply to this email directly, view it on...

Because the 'da_trainval_net.py' have 'next()' iteration,the T_domain datasets and S_domain datasets must equivalence？？

I have the same problem, have you soleved it?

Code release

Looking forward to your code~~~

很棒的工作，有一些问题想要请教你

> 我看到你的config文件夹里面有mmdetection格式的配置文件，请问一下，采用你论文里面的数据增强策略对于faster rcnn在coco数据集上有明显的提升吗？应该怎么添加你的数据增强策略到mmdetection里面呢？您好！我正打算把PSIS的工作复现在mmdetection上，请问您尝试了么？

IndexError: list index out of range

I met the same problem, have you fixed it? Thanks!