RunsongZhu

> Sorry for my late reply. I am not quite sure about your question. In the optimization-based pipeline, there is no network used, so we did not have any "training"...

Thanks for sharing your great work! There is a question I am confused. The dataset used in your paper is the core-version or the segmentation-version or others in ShapeNet dataset?...

> Hi! > > The dataset used is the core version. The data preparation code (`generate_local_points_dataset.py`), expects a simple flat directory of files as input; you may need to slightly...

> No problem! > > The file with train/test/val splits for ShapeNetCore is hosted separately here: http://shapenet.cs.stanford.edu/shapenet/obj-zip/SHREC16/all.csv (I have no idea why they don't include it in the zip, perhaps...

> @Runsong123 Can you let me know if you are training on a different dataset? If yes, can you help me by saying how to do that? Yes, I just...

> Hello, I also met the similar "Division by zero" error. I just add the small number (1e-5) to avoid it. Bests, Runsong