In data_processing.py, 43-45 lines shows how to get theta than trianed, but i don't un

Hi <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

Can't understand the angle trained in network about 3d-deepbox HOT 5 OPEN

smallcorgi commented on August 20, 2024

Can't understand the angle trained in network

from 3d-deepbox.

Comments (5)

smallcorgi commented on August 20, 2024

Hi @sdukaka,

It just orientates +pi/2, and it will subtract pi/2 in the final output.

from 3d-deepbox.

sdukaka commented on August 20, 2024

But this angel is only the degree between camera and object center and what we want to use in training stage is the difference of theta_ray - rotation_y(the obj's own rotation)

from 3d-deepbox.

smallcorgi commented on August 20, 2024

Yes, the outputs of network are 3D dimensions and observation angle of the object.

from 3d-deepbox.

jkstyle2 commented on August 20, 2024

@sdukaka Hi, have you figured out what the angle exactly means? I can't understand it at all. Could you please help me understand what we should train for?

from 3d-deepbox.

sdukaka commented on August 20, 2024

I think the angle what we should train for is between camera and object center. jaykay <[email protected]> 于2019年1月23日周三下午4:46写道：

…

@sdukaka <https://github.com/sdukaka> Hi, have you figured out what the angle exactly means? I can't understand it at all. Could you please help me understand what we should train for? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#7 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AIcfQnkVS48Xcv2UobGbQzSC0S30NfS9ks5vGCF2gaJpZM4RNPzb> .

from 3d-deepbox.

Recommend Projects