copick / bulk-evaluation / 0.0.3

Compare All Picks from Different Users and Sessions

A solution that uses the compare-picks album solution to evaluate all user_id and session_id pairs listed in a CSV file, creating JSON output files for each pair in a specified directory and submitting jobs to Slurm.

Arguments

--copick_config_path

Path to the Copick configuration JSON file. (default value: PARAMETER_VALUE)

--reference_user_id

User ID for the reference picks. (default value: PARAMETER_VALUE)

--reference_session_id

Session ID for the reference picks. (default value: PARAMETER_VALUE)

--distance_threshold

Distance threshold multiplier for matching points (e.g., 1.5x the radius as default). (default value: PARAMETER_VALUE)

--beta

Beta value for the F-beta score. (default value: PARAMETER_VALUE)

--output_directory

Directory to save the output JSON files. (default value: PARAMETER_VALUE)

--candidates_csv

Path to the CSV file containing user_id and session_id pairs to process. (default value: PARAMETER_VALUE)

--weights

JSON string with weights for each particle type. (default value: PARAMETER_VALUE)

--slurm_partition

Slurm partition to use. (default value: PARAMETER_VALUE)

--slurm_time

Time limit for the Slurm job (e.g., 01:00:00 for 1 hour). (default value: 24:00:00)

--slurm_memory

Memory limit for the Slurm job (e.g., 125G for 125 GB). (default value: 128G)

--slurm_cpus_per_task

Number of CPUs per Slurm task. (default value: 24)

--slurm_module_commands

Slurm module commands to load necessary modules (e.g., module load cuda/11.8.0_520.61.05\nmodule load cudnn/8.8.1.3_cuda11). (default value: PARAMETER_VALUE)

--submit_job

Whether to submit the job to Slurm or just print the submission command and script. (default value: 1)

Usage instructions

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