Closed maggie0106 closed 6 years ago
Hi Maggie,
The dataset is quite small (in some categories there are only 100 objects for training and a few for testing) so the result is not stable. What I usually do is to observe the loss curve and "early stop" the training at 200 or 250 epochs.
For stable evaluation I suggest you use the evaluation code which evaluates point cloud in all rotations instead of just the default rotation provided by ModelNet40.
Hope it helps
Hi Charles, Thanks for replying me! I will try the method u mentioned.
Cheers, Maggie
Hi, Thanks for sharing your amazing work! I have a quick question. I have trained several trails of the point net on the ModelNet 40 dataset with all the default parameters in the code. I saw quite big performance fluctuation during the training, so it's a bit hard to pinpoint when the model converges. So is there any way to alleviate this performance fluctuation problem? Thanks
Sincerely, Maggie