Closed themmes closed 7 years ago
Thanks for spotting that! I've fixed it.
You're welcome, did you also get a chance to look at the email I send you (charlesq34@gmail.com)?
Oh and btw, the typo is in all train.py
, so also sem_seg/train.py
oops, thanks again.
What's the title of the email? I cannot find any..
PointNet++ multi-scale (2questions, 2minread) Sent on 6th of July to charlesq34@gmail.com
Maybe interesting to sidenote; I am currently preparing the semantic3d.net datasets to perform Semantic Segmentation using your model.
Odd, I have send you a new email. Let me know if it does not reach you.
@themmes how did it go with semantic3d dataset? I'm really curious how well PointNet++ performs on the large scale outdoor data.
@belevtsoff Thanks for asking, I discussed this with Maxim Tatarchenko (@mtatarchenko, PhD from Freiburg). I discontinued the research on Semantic3D, mainly because I received another dataset (MLS, sadly not public) where I could exploit reference to the scanner. My train of thought here was that it could provide spatial reference in a similar way the PointNet on indoor exploits relative position in the room. I believe Maxim also discontinued the research on Semantic3D after getting results of about 17% accuracy.
Oh, I see, thanks! Did you and Maxim do experiments with vanilla PointNet or pointnet++ as well? Seems to me like it could have a considerable improvement for large datasets.
Hi,
A colleague of mine and I only tried the vanilla PointNet. PointNet++ should definitely produce better results.
Best, Maxim
Cheers guys. I'll let you know If I'll end up trying PointNet++ on some outdoor or aerial data.
@belevtsoff did you already perform the tests on outdoor data? I am currently working on a project on outdoor data and would be very interested in an exchange
@belevtsoff Yes, please keep us posted. I ended up moving to proprietary data of a highway scene with PointNet (achieved about 50% MIOU for four classes excl. background class) as the PointNet++ code was not yet released at that time.
@maximiliangoettgens I believe @tatarchm (or his colleague) results of PointNet on the Semantic3D dataset were about 20% MIOU for point-wise classification (or semantic segmentation / scene segmentation)
@maximiliangoettgens @themmes Hey guys, just noticed the messages. Unfortunately, I had to drop out of the project, so I never ended up trying PointNet++ on the outdoor data. I'll forward this conversation to the guys from the project, maybe they've tried something by now.
bump on whether pointnet++ was every applied to semantic3d benchmark? Does anyone have any updates?
Dear Charles,
In
sem_seg/train.py
probably a typo which eliminates your learning rate clipping, which you so emphasize.learing_rate
should belearning_rate
?