-
Notifications
You must be signed in to change notification settings - Fork 125
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
Trying to re-train planercnn with custom data #39
Comments
Hello |
Hi,
You should change the way that this class loads data, since PlaneRCNN loads
every planes in a World reference, and then transforms the parameters into
the respective frame.
A segunda, 1 de jun de 2020, 14:31, rjose97 <[email protected]>
escreveu:
… Hello
I'm trying to re-train with some custom data too. But I can't change
ScanNetScene Class in order to select the right segmentations for each
plane. Could you help me?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#39 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AKZGRBRED2CQ6IMNAVRLBOTRUOUSFANCNFSM4LFEJVYQ>
.
|
Hello, friend HuiYao |
@Hui-Yao were you able to train for custom images ? |
Hello guys, thanks a lot for sharing this code.
I'm trying to re-train with some custom data, where we have plane parameters for each frame. This way we changed ScanNetScene Class in order to select the right segmentations for each plane. However, we still need a 'plane_info' file in order to re-train with anchor_type = 'normal'. How could I fix this?
The text was updated successfully, but these errors were encountered: