config for different datasets

[houyongkuo]

Hello, thank you for your innovative work. I would like to ask how the config of different datasets is determined?

[HuguesTHOMAS]

The config for different datasets is mostly the same, only some data related parameters should change. There are numbers of issues where I already talked about config parameters. You can search in these previous issues for more details.

A few example: https://github.com/HuguesTHOMAS/KPConv-PyTorch/issues/90 https://github.com/HuguesTHOMAS/KPConv-PyTorch/issues/72 https://github.com/HuguesTHOMAS/KPConv-PyTorch/issues/5

[houyongkuo]

Thanks. I have another question: which variable represents each point feature or the extracted point feature.

[HuguesTHOMAS]

The point features are in the outputs of the network: https://github.com/HuguesTHOMAS/KPConv-PyTorch/blob/73e444d486cd6cb56122c3dd410e51c734064cfe/utils/trainer.py#L188

You can see them used in the validation function: https://github.com/HuguesTHOMAS/KPConv-PyTorch/blob/73e444d486cd6cb56122c3dd410e51c734064cfe/utils/trainer.py#L480-L484