Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"
Hello, thank you for your wonderful work. But I have some small problems. According to what standard should the parameters such as per-transformer, transformer, on_device_train_transform of the config file be adjusted after the network changes the new data set? Is the network sensitive to the parameters of config?
Hi @Rambler30, please have a close look at the 🧑🏫 tutorial slides and notebook, it was specifically created to help in this scenario. The video will also be released in the coming days.
If you ❤️ or use this project, don't forget to give it a ⭐, it means a lot to us !
Hello, thank you for your wonderful work. But I have some small problems. According to what standard should the parameters such as per-transformer, transformer, on_device_train_transform of the config file be adjusted after the network changes the new data set? Is the network sensitive to the parameters of config?