-
Notifications
You must be signed in to change notification settings - Fork 49
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Failed to solve pose #4
Comments
Hi @zyjluck , you get it ? I am facing the same issue. |
Same problem. Waiting for an answer. |
what's wrong, I can only get an identity matrix? |
so, have you solved this problem? |
Yes, I changed the device and it worked. GPU1660ti |
Yes, I changed the device and it worked. GPU :1660ti 6G |
It may be due to insufficient performance of the GPU. I changed the device and it worked. GPU :1660ti 6G |
Why it is GPU relevant and what are the essential reasons? My is GTX1080. -------- 原始邮件 --------发件人: SMX <[email protected]>日期: 2020年6月29日周一 15:14收件人: PRBonn/refusion <[email protected]>抄送: Zhengjun-Du <[email protected]>, Comment <[email protected]>主 题: Re: [PRBonn/refusion] Failed to solve pose (#4)
After compiling successfully, when I run ./refusion_example DATASET_PATH. All camera poses are identity matrices. I think it's because TSDF was not built successfully. Can you help me analyze the reason? Thank you!
so, have you solved this problem?
Yes, I changed the device and it worked. GPU :1660ti 6G
—You are receiving this because you commented.Reply to this email directly, view it on GitHub, or unsubscribe.
|
Because tsdf algorithm in refusion requires GPU to support parallel operation, if GPU memory is too small, tsdf construction cannot be completed. I also run successfully on the gtx1080 device. You can check whether your system environment is fully configured. Furthermore, you can change some parameters about GPU in tsdf algorithm |
thanks for your quick response! @zyjluck
|
After compiling successfully, when I run ./refusion_example DATASET_PATH. All camera poses are identity matrices. I think it's because TSDF was not built successfully. Can you help me analyze the reason? Thank you!
The text was updated successfully, but these errors were encountered: