cultionet
cultionet copied to clipboard
[bug] EdgeDataset processed path
I don't think that this affects functionality, but I did come across it.
When calling EdgeDataset, if I call ds = EdgeDataset(root = data_directory_path) where data_directory has the structure data_directory: processed: data1 data2 ...
Then the EdgeDataset.processed_paths have an additional 'data_directory_path/processed' at the the beginning of the path.
IE it results in 'data_directory_path/processed/data_directory_path/processed/data1' instead of 'data_directory_path/processed/data1'
That is the expected layout, but I will try to make it clearer in the README. Essentially, you just want to pass the base/parent directory.
That makes sense. I was exploring using a slightly different directory structure (specifically if I have the training data in a different location than data/processed).