Skip to content

Conversation

@ritvikvasan
Copy link
Contributor

@ritvikvasan ritvikvasan commented Apr 16, 2025

This PR addresses #88 , #87 , #71


Training these models can take days. We've published our trained models so you don't have to. Skip to the [next section](#2-model-inference) if you'd like to just use our models.

1. Create a single cell manifest (e.g. csv, parquet) for each dataset with a column corresponding to final processed paths, and create a split column corresponding to train/test/validation split.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we have info about which columns this manifest must have? Seems related to Yuichiro's question. What do you think?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Right now, if you run our preprocessing, then the column name for registered images in registered_path, column name for pointclouds is pointcloud_path, column name for segs is seg_path, and column name for sdfs is sdf_path. The name really can be anything, you just have to point to that column name in the config file...Im not sure I want to fix this name to something specific

@ritvikvasan ritvikvasan merged commit 98ca4bc into main Apr 16, 2025
1 check passed
@ritvikvasan ritvikvasan deleted the update_docs branch April 16, 2025 19:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants