Generalize data paths for any data source #23
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a PR to generalize handling of data sources. Currently the code makes assumptions that users will be using one of the provided training sets, but most likely people will want to evaluate on other training data or other parts of ShapeNet.
Changes the following things:
data_camera_mode
tomanifest_dir
-- the main function is to find the training and val text files once any specific logic has been generalized.use_shapenet_split
to always be true and remove the arg -- the other PR adds a script which properly splits data into 70/20/10 file manifests.Submitted as a draft, I am testing on some datasets now to make sure everything is working.