copick / split-dataset / 0.0.9

Split Dataset for Training and Testing

A solution that splits datasets into training and test sets, ensuring distributions are preserved.
Tags
imagingcryoet
Solution written by
Kevin Zhao and Kyle Harrington
License of solution
MIT
Source Code

Arguments

--copick_config_path
Path to the Copick configuration JSON file. (default value: PARAMETER_VALUE)
--ks_values
Comma-separated list of split ratios for train, test1, test2, and test3. (default value: PARAMETER_VALUE)
--output_json_path
Path to the output JSON file. (default value: PARAMETER_VALUE)
--user_id
User ID to filter picks. (default value: PARAMETER_VALUE)
--session_id
Session ID to filter picks. (default value: PARAMETER_VALUE)
--random_seed
Random seed for reproducibility. (default value: PARAMETER_VALUE)

Usage instructions

Please follow this link for details on how to install and run this solution.