Torben Peters

@harry1576 add the following to the initialization of ModelCheckpoint(object) self.data_config = OmegaConf.create(self._checkpoint.run_config["data"]) and remove the property for self.data_config

@chenchr This is not an "offical" repository of the Author/KIT, I would suggest to ask cvlibs.net for more data.

Hello, Yes of course you can link it to your homepage! I´m very open to any changes/Issues EDIT: I´ve changed my username to my abbr. in case of confusion

@nischnei I've added the kernel_regularization and changed the bias init. to zero.

Hi Pierre, as you can see in the python code there is already a very short example. The method sparse_conv outputs the convolved image and the propagated binary mask. the...

Hello andThank you i've changed it! In the Paper in Figure 2 you can see that pool and kernel size are equal.

The Pointcloud object has the following methods for me: ['__class__', '__delattr__', '__doc__', '__format__', '__getattribute__', '__getitem__', '__hash__', '__init__', '__new__', '__pyx_vtable__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', '_from_pcd_file', '_from_ply_file', '_to_pcd_file', '_to_ply_file',...