search

drprojects / superpoint_transformer

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"
MIT License
546 stars 71 forks source link

Raw and Processed file #57

Closed ywang864 closed 8 months ago

ywang864 commented 8 months ago

image A quick question, where are these two data files come from?

drprojects commented 8 months ago

If you read the lines just below your screenshot on the documentation page:

Automatic download and preprocessing

Following torch_geometric's Dataset behavior:

Dataset instantiation ➡ Load preprocessed data in data/<dataset_name>/processed

Missing files in data/<dataset_name>/processed structure ➡ Automatic preprocessing using files in data/<dataset_name>/raw

Missing files in data/<dataset_name>/raw structure ➡ Automatic unzipping of the downloaded dataset in data/<dataset_name>

Missing downloaded dataset in data/<dataset_name> structure ➡ Automatic manual download to data/<dataset_name>

Said otherwise, you need to download the zip files as indicated, then the program will unzip what it needs in raw/ and will save the preprocessed files in processed/.