ruomingzhai
ruomingzhai
> Is this during training or inference? During training
> Ah yes. The hard cutoff is the maximum number of "valid" superpoints to embed with the CloudEmbedder. A superpoint is valid if it has more than `args.ptn_minpts` points. Indeed,...
Hi @drprojects . I have manually downlad the no_xyz s3dis dataset. The S3DIS download automation also bothers me because in the default _download function in torch_geometric/data/dataset.py. ` def _download(self): if...
> Hi @ruomingzhai, I am currently out of office and kind of off-the-grid until mid september. > > I will try to help you in the meantime. As you saw,...
> Hi @ruomingzhai @Cemm23333 can you please let me know if the above message solved your issue ? Thanks a lot! It works as I put the manually downloaded dataset...
Furthermore, I have tried build 2D graph using its pixel coordinates, but the results is not good. The number of partitions are all one which means it did not partition...
Dear loicland, Thank you for your detailed instruction. I constructed the graph with 8-neighborhod in this 512 x 512 image and iteratively run it with reg_strength from 0.01 to 0.8...
Thank you! It works on your project img2svg!